Wire up dynamic agent registry, integrations, agent-time tracking, UI modernization

- server.py: dynamic agent execution engine (cli/http/mcp), live agent
  registry (/api/agents register/unregister), integrations API, agent stats
  & skill scoring, kanban task delete, plugin uninstall, agent-time tracking
  + /test page
- dashboard: modernized agent-health, plugins marketplace, smart-router,
  styles; added agent-time monitor page + terminal page
- scheduler.py rewrite; start.sh / start-agentic-os.sh improvements
- skills: added firebase-*, notion-knowledge-capture, xcode-project-setup,
  audit/test plugins; updated learnings across skills
- brain/ docs + data registry files (agent-registry, integrations, router-keywords)
- .gitignore: exclude runtime artifacts (pid, graphify-out, logs)

Verified live on :8081 - all new endpoints return 200 and register/unregister
persists to data/agent-registry.json.

.gitignore

@@ -11,3 +11,8 @@ audit/*
 data/settings.json
 data/chat-history.json
 data/cost-history.json
+.agentic-os.pid
+graphify-out/
+brain/graphify-out/
+skills/*/graphify-out/
+*.log

AGENTS.md

@@ -317,7 +317,7 @@ Your role is to act as the **kernel** of this system: route tasks to the right a
 | Detail | Info |
 |--------|------|
 | **Budget** | Strictly free tiers (GCP Free, GitHub Student Pack, Colab, Kaggle) |
-| **Active Project** | CloudMart — GCP DevOps multi-region e-commerce platform |
+|| **Active Projects** | Kitchen-Inventory (catering kitchen management on antigravity), Pendleton-comms-live (walkie talkie for catering events on Railway) |
 | **CLI Tools Available** | opencode, Hermes Agent, Gemini CLI |
 | **Preferred Model** | Hermes: Owl Alpha (OpenRouter, free), opencode: deepseek-v4-flash-free (opencode-zen), Gemini: gemini-2.5-flash (Google OAuth) |
 

CHANGELOG.md

@@ -0,0 +1,72 @@
+# Changelog
+
+All notable changes to Agentic OS will be documented in this file.
+
+## [v1.3.0] - 2026-06-28
+
+### Added
+- **Web Terminal** — Full bash shell in browser via xterm.js + WebSocket PTY (port 8082)
+  - 256-color support, terminal resizing, 10k line scrollback
+  - Reconnect and clear buttons
+  - Dark theme matching dashboard
+- **Dynamic Agent Registry** — Register/remove custom agents via dashboard or API
+  - `GET /api/agents` — list all agents
+  - `POST /api/agents/register` — add custom agent (CLI, HTTP, or MCP type)
+  - `DELETE /api/agents/:name` — remove custom agent
+  - Agent config stored in `data/agent-registry.json`
+  - Custom agents auto-appear in status, health, router
+- **Agent Health Dashboard** — Complete rewrite
+  - Card grid view with status indicators
+  - Registry table with type/source/actions
+  - "Add Agent" modal with form (name, binary, run args, health check, router keywords)
+  - Remove button for custom agents
+- **Smart Router Extensibility** — Custom agents can register routing keywords via `data/router-keywords.json`
+
+### Changed
+- **Hermes Model** — Switched from `openrouter/owl-alpha` to free model chain:
+  1. `qwen/qwen3-next-80b-a3b-instruct:free` (primary)
+  2. `openai/gpt-oss-120b:free` (fallback 1)
+  3. `google/gemma-4-31b-it:free` (fallback 2)
+  4. `nvidia/nemotron-3-super-120b-a12b:free` (fallback 3)
+- **Agent Discovery** — All endpoints now use dynamic registry instead of hardcoded `["opencode", "hermes", "gemini"]`
+  - `/api/status`, `/api/agents/health`, `/api/chat`, `/api/router/route`, `/api/agents/:name/stats`
+- **Base URL** — Hermes now points to `https://openrouter.ai/api/v1` directly
+
+### Fixed
+- Audit log malformed timestamp entry removed
+- Test artifacts cleaned from kanban, goals, cost history, brain
+
+## [v1.2.0] - 2026-06-26
+
+### Added
+- Agent profiles (`agents/{opencode,hermes,gemini}/`)
+- APScheduler integration (`scheduler/scheduler.py`)
+- Plugin install from git repo or template (`POST /api/plugins/install`)
+- Connected apps / integrations system
+
+## [v1.1.0] - 2026-06-05
+
+### Added
+- Kanban board (6-column, 13 API endpoints)
+- Goals system with auto-sync to `brain/active-projects.md`
+- Journal with daily entries and full-text search
+- Agent health monitoring (3 endpoints)
+- Smart Router with keyword-based task routing
+- Learning Analytics (skill eval scores, trends)
+- Session Replay (browse opencode logs)
+- Cost Analytics (token usage tracking)
+- Backup/restore system (tar.gz snapshots)
+
+## [v1.0.0] - 2026-05-17
+
+### Added
+- Initial release
+- FastAPI backend (58+ endpoints)
+- Vanilla JS SPA dashboard (21 pages)
+- 3 built-in agents: OpenCode, Hermes, Gemini CLI
+- 16 skills with eval scoring
+- Brain/memory system (markdown files)
+- Scheduler (APScheduler + Hermes cron)
+- Plugin registry
+- Standards system
+- Prompt templates

OPERATIONAL-NOTES.md

@@ -0,0 +1,28 @@
+# Operational Notes
+
+## Server Debugging
+- Logs: `tail -f /tmp/agentic-os.log`
+- If browser shows blank dashboard, check for a single failing API endpoint crashing the SPA
+- Malformed JSON in `audit.log` can crash `/api/audit` — the server skips bad lines but check if it's persistent
+
+## WSL → Windows Browser
+- Server-side 500 errors can look like connection failures from Windows browser
+- WSL2 loopback and Windows loopback are separate interfaces — use `127.0.0.1` from WSL, not `localhost` from Windows
+
+## Hermes Config
+- Config: `~/.hermes/config.yaml`
+- API keys: `~/.hermes/.env`
+- Current model: `qwen/qwen3-next-80b-a3b-instruct:free` (OpenRouter)
+- Fallbacks: gpt-oss-120b:free → gemma-4-31b-it:free → nemotron-3-super-120b:free
+- Change model: `hermes config set model.default <model-id>`
+
+## Agentic OS Docs
+- Full docs: `docs/README.md`
+- Changelog: `CHANGELOG.md`
+- After API changes: `python3 scripts/update-api-docs.py`
+- Skill: `software-development/agentic-os-docs`
+
+## Brain Guardian Cron
+- Job ID: `68221afb4d45`
+- Runs every 2h via Hermes cron
+- Outputs: brain/health-report.md, brain/skill-usage.md, brain/github-activity.md

agents/hermes/USER.md

@@ -3,7 +3,7 @@
 ## User
 - Name: User
 - Tech Stack: opencode, Hermes Agent, Gemini CLI, deepseek-v4-flash-free
-- Projects: CloudMart (GCP DevOps), Agentic OS
+- Projects: Kitchen-Inventory (catering kitchen management on antigravity), Pendleton-comms-live (walkie talkie on Railway), Agentic OS
 - Budget: Free tiers only
 
 ## Preferences

brain/active-projects.md

@@ -6,7 +6,25 @@
 - Building complete agent orchestration platform
 - 8 phases planned
 
-## CloudMart
+## Kitchen-Inventory (Active)
-- Status: Active (ongoing)
+- Status: In development — catering kitchen management system
-- GCP DevOps multi-region e-commerce platform
+- Deployed on antigravity (server/host)
-- GKE Autopilot, Cloud SQL, Cloud CDN, Istio, Next.js
+- Key features: invoice scanner (AI vision), barcode scanner, shelf life tracker, vendor invoice parsing
+- Pipeline: Invoice image → pre-process → Gemini vision (primary) → GPT-5.5 (backup) → vendor detection → Claude (text→JSON) → math audit → Firebase write
+- Vendor invoices: Sysco, Vern's, US Foods (each with custom prompts)
+- Shelf scans: photo → Gemini → JSON array of items
+- Code under review: geminiService.ts has 18 issues (4 critical) — wrong shelf prompt in GPT fallback, analyzeImage ignores prompt, no shelf retries, bad model names, bare catches
+
+## Pendelton-comms-live (Active)
+- Status: In development — real-time voice communication app for catering events
+- Purpose: Walkie talkie for employees spread out at big catering events
+- GitHub: https://github.com/Linecheck-store/Pendelton-comms-live (private)
+- Last worked on: 2026-02-28
+- Tech: Node.js + Express + Socket.IO signaling, React + TypeScript frontend
+- Audio: WebRTC peer-to-peer, STUN/TURN configured
+- Deployed on Railway
+- Known issues: audio cutting out on mobile Safari, reconnection logic needs improvement
+
+- [Ship Agentic OS v1](goal:c24b3d85) — Complete audit and fix all issues
+
+- [Push everything in the Kanban board down the line](goal:2c4b22ac) — It involves different skills to get different things done.

brain/business-brain.md

@@ -19,7 +19,7 @@ Agentic OS is a multi-agent orchestration platform that coordinates opencode, He
 ## Key Relationships
 - User: Developer — AI/ML and DevOps enthusiast
 - Tool stack: opencode, Hermes Agent, Gemini CLI, deepseek-v4-flash-free
-- Active projects: CloudMart (GCP DevOps), Agentic OS
+- Active projects: Kitchen-Inventory (on antigravity), Pendleton-comms-live (on Railway)
 
 ## Standing Decisions
 - All memory is stored in markdown for cross-agent compatibility

brain/github-activity.md

@@ -0,0 +1,19 @@
+# GitHub Activity Log
+
+> Last checked: 2026-07-25 09:44
+
+## Project: Agentic OS
+- Repo: ~/agentic-os (github.com/modimihir07/agentic-os)
+- Last commit: d9b1b0d "Update Hermes MEMORY.md with v0.2.0 features" (2026-06-05)
+- Unpushed: 0 commits
+- Recent (48h): none — last commit 50 days ago
+- Uncommitted local changes: AGENTS.md, agents/hermes/USER.md (modified, not committed)
+
+## Project: Kitchen-Inventory
+- Repo: not cloned locally (deployed on antigravity server/host)
+- No git activity data available from this machine
+
+## Project: Pendelton-comms-live
+- Repo: https://github.com/Linecheck-store/Pendelton-comms-live (private)
+- Not cloned locally — no git activity data available
+- Last worked on: 2026-02-28 (per active-projects.md)

brain/health-report.md

@@ -0,0 +1,32 @@
+# Brain Health Report
+
+> Generated: 2026-07-25 09:45
+
+## Status: needs attention (activity stale ~8 days)
+
+### Memory Files
+- memory.md: 208 words (OK, limit 600)
+- active-projects.md: 3 projects (2 need status refresh)
+- log.md: 23 lines (OK)
+- recent-decisions.md: 1 entry, 68 words (OK)
+
+### Projects
+- Agentic OS: Building Phase 1 — last commit 2026-06-05 (50 days ago); uncommitted changes to AGENTS.md and agents/hermes/USER.md sitting in working tree
+- Kitchen-Inventory: In development — repo not cloned locally; geminiService.ts still flagged with 18 issues (4 critical) awaiting fixes
+- Pendelton-comms-live: STALE — last worked on 2026-02-28 (~5 months); repo not cloned locally
+
+### GitHub
+- Agentic OS: 0 commits in 48h, 0 unpushed, 2 modified files uncommitted
+- Kitchen-Inventory / Pendelton-comms-live: repos not cloned locally — no data
+
+### Skills
+- 2 skills with new learnings since 2026-06-28 (memory-consolidation, firebase-hosting-basics — both 2026-07-17)
+- 0 skills with eval data (all 18 score-history.json files empty)
+- Last skill_run: memory-consolidation 2026-07-17 (one run timed out)
+- Recurring problem: agent timeouts on skill runs (opencode 06-28, hermes 07-17)
+
+### Alerts
+1. All 3 projects show no activity in the past week — flag for review.
+2. Uncommitted changes in ~/agentic-os (AGENTS.md, agents/hermes/USER.md) — commit or discard.
+3. Eval scoring system unused — score-history.json files never populated.
+4. Kitchen-Inventory critical code-review findings (geminiService.ts) still open.

brain/journal/2026-06-25.md

@@ -0,0 +1 @@
+Journal entry content verification test

brain/journal/2026-06-28.md

@@ -0,0 +1 @@
+I got to figure out how to get the KanBan Board working right.

brain/log.md

@@ -0,0 +1,23 @@
+# Wiki Log
+
+> Chronological record of all wiki actions. Append-only.
+> Format: `## [YYYY-MM-DD] action | subject`
+> Actions: ingest, update, query, lint, create, archive, delete
+> When this file exceeds 500 entries, rotate: rename to log-YYYY.md, start fresh.
+
+## [2026-06-26] create | Wiki initialized
+- Domain: Personal knowledge base (general-purpose second brain)
+- Structure created with SCHEMA.md, index.md, log.md
+- Directories: raw/{articles,papers,transcripts,assets}, entities, concepts, comparisons, queries
+
+## [2026-06-26] ingest | Second Brain User Guide
+- Source: user-provided document (full user guide)
+- Created: concepts/second-brain-user-guide.md, concepts/gtd.md
+- Updated: index.md (2 new entries, total: 3)
+- Key topics: inbox workflow, page types, knowledge graph, journaling, people/project/idea/reference tracking, import/export, backup
+
+## [2026-06-28] update | Project memory cleanup
+- Removed CloudMart reference (not an active project)
+- Added Kitchen-Inventory: catering kitchen management system (on antigravity) — invoice scanner, barcode scanner, shelf life tracker
+- Added Pendleton-comms-live: walkie talkie app for catering events (on Railway) — WebRTC, Socket.IO, React/TS
+- Updated: active-projects.md, memory.md, business-brain.md, AGENTS.md

brain/memory.md

@@ -4,6 +4,7 @@
 - 3 agents configured: opencode, Hermes Agent, Gemini CLI
 - Dashboard runs on FastAPI (Python) — localhost only
 - All skills follow _template/ convention
+- Memory consolidation: 2026-07-17 (run — all files clean, stale truncated run log from 2026-06-29 cleaned)
 
 ## User
 - Name: User
@@ -11,9 +12,19 @@
 
 ## Active Work
 - Building Agentic OS from scratch (May 17, 2026)
-- CloudMart GCP DevOps project ongoing
+- Kitchen-Inventory — catering kitchen management system (on antigravity)
+- Pendleton-comms-live — walkie talkie app for catering events (on Railway)
 
 ## Technology Preferences
 - Preferred model: deepseek-v4-flash-free
 - Free tiers: GCP Free, GitHub Student Dev Pack, Colab, Kaggle
 - Knowledge management via markdown vaults
+
+## Consolidated Insights (2026-06-29)
+- **opencode** times out on non-code tasks (brainstorming, tdd-cycle, backup-skill, code-review, goal-planner, test-plugin) — route these to hermes
+- **hermes** can also time out on complex multi-step tasks — keep queries short
+- **daily-standup** is the most-run skill; hermes executes faster than opencode for it
+- **Score tracking**: all 18 skills have empty score-history.json — no eval data yet
+- **All learnings files** are concise (under 200 words each), no compression needed
+- **No contradictions** found across skill learnings
+- **recent-decisions.md**: 3 entries archived (all from 2026-05-17), 0 recent — no archiving needed

brain/recent-decisions.md

@@ -1,6 +1,10 @@
 # Recent Decisions
 
-## 2026-05-17
+(No decisions in the last 30 days)
+
+## Archived (older than 30 days)
+
+### 2026-05-17
 - Created Agentic OS project structure
 - 3-agent architecture: opencode (code) + Hermes (memory/channels) + Gemini CLI (research)
 - Web dashboard only (no CLI dashboard) — FastAPI + vanilla JS SPA

brain/skill-usage.md

@@ -0,0 +1,38 @@
+# Skill Usage & Effectiveness
+
+> Last updated: 2026-07-25
+
+## Audit Log Summary (164 total entries)
+| Action | Count |
+|--------|-------|
+| kanban_task_updated | 31 |
+| skill_run | 22 |
+| chat_message | 15 |
+| brain_update | 11 |
+| journal_saved | 10 |
+| settings_updated | 9 |
+| kanban_task_created | 8 |
+| agent_registered | 7 |
+| task_routed | 5 |
+| standards_discovery_run | 5 |
+
+## Recent Skill Runs
+| Skill | Agent | Last Run | Result |
+|-------|-------|----------|--------|
+| memory-consolidation | hermes | 2026-07-17 | 1 completed, 1 timeout |
+| firebase-hosting-basics | opencode | 2026-06-28 | timeout |
+
+## Eval Scores
+- All 18 score-history.json files are empty — no eval data has accumulated yet.
+
+## New Learnings Since 2026-06-28
+- memory-consolidation/learnings.md (updated 2026-07-17)
+- firebase-hosting-basics/learnings.md (updated 2026-07-17)
+- goal-planner, code-review, test-plugin (updated 2026-06-29)
+
+## Skills Per Project
+| Project | Skills Used |
+|---------|-------------|
+| Agentic OS | memory-consolidation, brain-guardian (Hermes cron), daily-standup, heartbeat |
+| Kitchen-Inventory | code-review, firebase-hosting-basics |
+| Pendelton-comms-live | (none recorded) |

dashboard/AGENT_TIME_MONITOR.md

@@ -0,0 +1,65 @@
+# Agentic-OS · Agent Time Monitor
+
+A localhost dashboard that tracks **total time the AI agents spent on the
+agentic-os project**, plus an embedded graphify knowledge-graph view of the
+codebase, with one-click sync of the total to **Mnemoverse** persistent memory.
+
+## What it measures
+The project's logs (`audit/audit.log`, `data/chat-history.json`,
+`data/cost-history.json`) record *events* (a chat, a skill run, a write)
+but not explicit session durations. Total agent time is therefore **estimated**
+with a session-gap model:
+
+- Each logged event is a timestamped "touch" by an agent.
+- A *session* for an agent = a run of touches where each touch is within
+  `GAP` seconds (default 30 min) of the previous one.
+- Session duration = (last touch − first touch) + `TAIL` (default 2 min, to
+  account for work after the last logged event).
+- `total_seconds` = sum of all an agent's session durations.
+
+This is clearly labeled as an ESTIMATE in the UI. Tune `GAP`/`TAIL` via the
+`AGENT_TIME_GAP` / `AGENT_TIME_TAIL` env vars.
+
+## Run it
+    cd ~/agentic-os
+    ./dashboard/start-monitor.sh            # default port 8765
+    # or:  python3 dashboard/serve_monitor.py --port 8765
+
+Then open:
+    http://localhost:8765/dashboard/pages/agent-time-monitor.html
+
+(Visiting http://localhost:8765/ redirects to the dashboard.)
+
+## Endpoints (server: dashboard/serve_monitor.py)
+- `GET  /`                                   → redirect to dashboard
+- `GET  /dashboard/.../agent-time-monitor.html` → the dashboard UI
+- `GET  /data/agent-time.json`               → computed report (totals + per-agent)
+- `GET  /graphify-out/graph.html`            → graphify code knowledge graph
+- `POST /recompute`                          → re-run the analyzer from logs
+- `POST /sync-mnemoverse`                    → push total to Mnemoverse (graceful)
+
+## graphify integration
+The interactive graph is produced by graphify (code-only, no API key needed):
+
+    cd ~/agentic-os
+    graphify . --code-only        # writes graphify-out/{graph.json,graph.html,GRAPH_REPORT.md}
+
+Rebuild any time the codebase changes; the dashboard iframe picks it up live.
+
+## Mnemoverse integration
+Set your key to enable the "Sync total to Mnemoverse" button:
+
+    export MNEMOVERSE_API_KEY=mk_live_xxxxxxxx
+    ./dashboard/start-monitor.sh
+
+The server calls `https://core.mnemoverse.com/api/v1/memory/write` with a
+single memory holding the total agent time, the agent count, and the method.
+Without a key (or offline) the button reports a clear, graceful message
+instead of failing.
+
+## Files
+- `scripts/analyze_agent_time.py`  — derives total/per-agent time from logs
+- `dashboard/serve_monitor.py`     — localhost server (stdlib only)
+- `dashboard/pages/agent-time-monitor.html` — the dashboard UI
+- `data/agent-time.json`           — last computed report (regenerated each run)
+- `graphify-out/`                  — graphify graph (built separately)

dashboard/api.js

@@ -41,7 +41,10 @@ const api = {
   getCost: () => api.get('/api/cost'),
   recordCost: (data) => api.post('/api/cost/record', data),
   getPlugins: () => api.get('/api/plugins'),
-  installPlugin: (name) => api.post('/api/plugins/install', { name }),
+  installPlugin: (name, repo_url) => api.post('/api/plugins/install', { name, repo_url }),
+  uninstallPlugin: (name) => api.del(`/api/plugins/${encodeURIComponent(name)}`),
+  getIntegrations: () => api.get('/api/integrations'),
+  addIntegration: (name, url, type) => api.post('/api/integrations', { name, url, type }),
   getBackups: () => api.get('/api/backups'),
   createBackup: () => api.post('/api/backup'),
   restoreBackup: (file) => api.post('/api/backup/restore', { file }),
@@ -89,4 +92,11 @@ const api = {
   // Session Replay
   listSessions: () => api.get('/api/sessions/list'),
   getSessionReplay: (id) => api.get(`/api/sessions/${encodeURIComponent(id)}/replay`),
+  // Agent Time Monitor
+  getAgentTime: (recompute = false) => api.get(`/api/agent-time${recompute ? '?recompute=true' : ''}`),
+  recomputeAgentTime: () => api.post('/api/agent-time/recompute', {}),
+  // Agent Registry
+  getAgents: () => api.get('/api/agents'),
+  registerAgent: (data) => api.post('/api/agents/register', data),
+  unregisterAgent: (name) => api.del(`/api/agents/${encodeURIComponent(name)}`),
 };

dashboard/index.html

@@ -8,6 +8,7 @@
 <link rel="preconnect" href="https://fonts.googleapis.com">
 <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800&display=swap" rel="stylesheet">
 <link rel="stylesheet" href="styles.css">
+<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/xterm@5.3.0/css/xterm.css">
 <script src="https://cdn.jsdelivr.net/npm/chart.js@4.4.7/dist/chart.umd.min.js"></script>
 </head>
 <body>
@@ -33,6 +34,7 @@
     <div class="sidebar-nav">
       <div class="sidebar-section"><div class="sidebar-section-label">Primary</div></div>
       <a href="#chat" class="nav-item" data-page="chat"><span class="nav-icon">💬</span><span class="nav-label">AI Chat</span></a>
+      <a href="#terminal" class="nav-item" data-page="terminal"><span class="nav-icon">⌨</span><span class="nav-label">Terminal</span></a>
       <a href="#dashboard" class="nav-item active" data-page="dashboard"><span class="nav-icon">◉</span><span class="nav-label">Dashboard</span></a>
       <div class="sidebar-section"><div class="sidebar-section-label">Agents</div></div>
       <a href="#skills" class="nav-item" data-page="skills"><span class="nav-icon">⚡</span><span class="nav-label">Skills</span><span class="nav-badge" id="skillCount">0</span></a>
@@ -48,6 +50,7 @@
       <a href="#smart-router" class="nav-item" data-page="smart-router"><span class="nav-icon">🧭</span><span class="nav-label">Smart Router</span></a>
       <a href="#learning-analytics" class="nav-item" data-page="learning-analytics"><span class="nav-icon">📊</span><span class="nav-label">Learning Analytics</span></a>
       <a href="#session-replay" class="nav-item" data-page="session-replay"><span class="nav-icon">🔄</span><span class="nav-label">Session Replay</span></a>
+      <a href="#agent-time" class="nav-item" data-page="agent-time"><span class="nav-icon">⏱</span><span class="nav-label">Agent Time</span></a>
       <div class="sidebar-section"><div class="sidebar-section-label">Management</div></div>
       <a href="#cost" class="nav-item" data-page="cost"><span class="nav-icon">💰</span><span class="nav-label">Cost Analytics</span></a>
       <a href="#plugins" class="nav-item" data-page="plugins"><span class="nav-icon">🔌</span><span class="nav-label">Plugins</span></a>

dashboard/pages/agent-health.js

@@ -1,115 +1,220 @@
-let agentHealthInterval = null;
-
 async function renderAgentHealth() {
   const content = document.getElementById('pageContent');
   content.innerHTML = `
     <div class="page-header">
       <div class="page-header-left">
-        <div class="page-title">Agent Health</div>
+        <h1 class="page-title">Agent Health</h1>
-        <div class="page-subtitle">Real-time monitoring of all 3 agents</div>
+        <p class="page-subtitle">Monitor and manage all connected agents</p>
       </div>
       <div class="btn-group">
-        <label class="switch" title="Auto-refresh every 5s">
+        <button class="btn btn-ghost" onclick="loadAgents()">↻ Refresh</button>
-          <input type="checkbox" id="healthAutoRefresh" checked onchange="toggleHealthAutoRefresh()">
+        <button class="btn btn-primary" onclick="showAddAgentModal()">+ Add Agent</button>
-          <span class="switch-slider"></span>
-        </label>
-        <span class="text-sm text-muted">Auto</span>
-        <button class="btn btn-primary" onclick="refreshAgentHealth()">🔄 Refresh Now</button>
       </div>
     </div>
-    <div id="agentHealthCards" class="grid grid-3" style="margin-bottom:20px">
+    <div id="agentCards" class="grid grid-3">
-      <div class="skeleton" style="height:180px"></div>
+      <div class="card"><div class="skeleton" style="height:120px"></div></div>
-      <div class="skeleton" style="height:180px"></div>
+      <div class="card"><div class="skeleton" style="height:120px"></div></div>
-      <div class="skeleton" style="height:180px"></div>
+      <div class="card"><div class="skeleton" style="height:120px"></div></div>
     </div>
-    <div class="section-title">Health Overview</div>
+    <div class="card mt-4">
-    <div class="card" id="healthOverviewCard">
+      <div class="card-header"><span class="card-title">Agent Registry</span></div>
-      <div class="loading"><div class="loading-spinner"></div><span>Loading health data...</span></div>
+      <div id="agentTable"></div>
     </div>
   `;
-  await refreshAgentHealth();
+  await loadAgents();
-  if (document.getElementById('healthAutoRefresh')?.checked) {
-    startHealthAutoRefresh();
-  }
 }
 
-function startHealthAutoRefresh() {
+async function loadAgents() {
-  stopHealthAutoRefresh();
-  agentHealthInterval = setInterval(refreshAgentHealth, 5000);
-}
-
-function stopHealthAutoRefresh() {
-  if (agentHealthInterval) {
-    clearInterval(agentHealthInterval);
-    agentHealthInterval = null;
-  }
-}
-
-function toggleHealthAutoRefresh() {
-  if (document.getElementById('healthAutoRefresh')?.checked) {
-    startHealthAutoRefresh();
-  } else {
-    stopHealthAutoRefresh();
-  }
-}
-
-async function refreshAgentHealth() {
   try {
-    const data = await api.getAgentHealth();
+    const { agents } = await api.getAgents();
-    const agents = data.agents || [];
+    const container = document.getElementById('agentCards');
-    const cards = document.getElementById('agentHealthCards');
+    const table = document.getElementById('agentTable');
-    if (!cards) return;
+
-    const agentIcons = { opencode: '🔧', hermes: '⚡', gemini: '🧠' };
+    // Card view
-    const agentColors = { opencode: 'purple', hermes: 'green', gemini: 'blue' };
+    container.innerHTML = agents.map(a => {
-    cards.innerHTML = agents.map(a => `
+      const sc = statusColor(a.status);
-      <div class="agent-health-card">
+      return `
-        <div class="agent-health-avatar" style="background:var(--${agentColors[a.name] || 'accent'}-dim);color:var(--${agentColors[a.name] || 'accent'})">
+        <div class="card agent-card">
-          ${agentIcons[a.name] || '🤖'}
+          <div class="agent-card-header">
-        </div>
+            <div class="agent-dot ${a.status}" style="width:12px;height:12px"></div>
-        <div class="agent-health-info">
+            <span style="font-weight:600;font-size:15px">${escapeHtml(a.display_name || a.name)}</span>
-          <div class="agent-health-name" style="text-transform:capitalize">${a.name}</div>
+            ${a.builtin ? '<span class="nav-badge" style="background:var(--accent)">built-in</span>' : '<span class="nav-badge" style="background:var(--green)">custom</span>'}
-          <div class="agent-health-status">
-            <span class="agent-dot ${a.status === 'online' ? 'online' : a.status === 'warning' ? 'warning' : 'offline'}"></span>
-            <span style="text-transform:capitalize;color:var(--text-secondary)">${a.status}</span>
           </div>
-          <div class="agent-health-stats">
+          <div style="font-size:12px;color:var(--text-secondary);margin:8px 0">${escapeHtml(a.description || 'No description')}</div>
-            <div class="agent-health-stat">
+          <div style="display:flex;gap:8px;align-items:center">
-              <div class="agent-health-stat-value" style="color:var(--green)">${a.status === 'online' ? '100' : '0'}%</div>
+            <span style="font-size:11px;color:${sc.text};text-transform:uppercase;font-weight:600">${a.status}</span>
-              <div class="agent-health-stat-label">Uptime</div>
+            <span style="font-size:11px;color:var(--text-muted)">${a.type || 'cli'}</span>
-            </div>
-            <div class="agent-health-stat">
-              <div class="agent-health-stat-value" style="color:var(--accent-light)">${a.status === 'online' ? '✓' : '✗'}</div>
-              <div class="agent-health-stat-label">Reachable</div>
-            </div>
-            <div class="agent-health-stat">
-              <div class="agent-health-stat-value text-sm" style="font-size:11px;color:var(--text-muted)">${new Date(data.updated).toLocaleTimeString()}</div>
-              <div class="agent-health-stat-label">Last Check</div>
-            </div>
-          </div>
-        </div>
-      </div>
-    `).join('');
-    const overview = document.getElementById('healthOverviewCard');
-    if (overview) {
-      const online = agents.filter(a => a.status === 'online').length;
-      const total = agents.length;
-      overview.innerHTML = `
-        <div style="display:flex;align-items:center;justify-content:space-between">
-          <div>
-            <div style="font-size:14px;font-weight:600">System Status</div>
-            <div style="font-size:12px;color:var(--text-secondary);margin-top:4px">
-              ${online}/${total} agents online · Last updated: ${new Date(data.updated).toLocaleTimeString()}
-            </div>
-          </div>
-          <div class="status-indicator ${online === total ? 'online' : online > 0 ? 'warning' : 'offline'}">
-            <span class="agent-dot ${online === total ? 'online' : online > 0 ? 'warning' : 'offline'}"></span>
-            ${online === total ? 'All Online' : online > 0 ? 'Partial' : 'Offline'}
           </div>
+          ${!a.builtin ? `<div style="margin-top:12px"><button class="btn btn-ghost btn-sm" onclick="removeAgent('${a.name}')">Remove</button></div>` : ''}
         </div>
       `;
-    }
+    }).join('');
+
+    // Table view
+    table.innerHTML = `
+      <table class="agent-table">
+        <thead>
+          <tr>
+            <th>Agent</th>
+            <th>Type</th>
+            <th>Status</th>
+            <th>Source</th>
+            <th>Actions</th>
+          </tr>
+        </thead>
+        <tbody>
+          ${agents.map(a => `
+            <tr>
+              <td>
+                <div style="display:flex;align-items:center;gap:8px">
+                  <div class="agent-dot ${a.status}" style="width:8px;height:8px"></div>
+                  <span style="font-weight:500">${escapeHtml(a.display_name || a.name)}</span>
+                </div>
+                <div style="font-size:11px;color:var(--text-muted);margin-top:2px">${escapeHtml(a.description || '')}</div>
+              </td>
+              <td style="text-transform:uppercase;font-size:11px">${a.type || 'cli'}</td>
+              <td><span style="color:${statusColor(a.status).text};font-size:11px;text-transform:uppercase;font-weight:600">${a.status}</span></td>
+              <td>${a.builtin ? '<span style="color:var(--text-muted)">built-in</span>' : '<span style="color:var(--green)">custom</span>'}</td>
+              <td>
+                ${!a.builtin ? `<button class="btn btn-ghost btn-sm" onclick="removeAgent('${a.name}')">Remove</button>` : '<span style="color:var(--text-muted);font-size:11px">—</span>'}
+              </td>
+            </tr>
+          `).join('')}
+        </tbody>
+      </table>
+    `;
   } catch (err) {
-    const cards = document.getElementById('agentHealthCards');
+    document.getElementById('agentCards').innerHTML = `<div class="card" style="grid-column:1/-1"><div class="empty-state"><div class="empty-state-icon">⚠</div><div class="empty-state-title">Error</div><div class="empty-state-desc">${escapeHtml(err.message)}</div></div></div>`;
-    if (cards) cards.innerHTML = `<div class="empty-state" style="grid-column:1/-1"><div class="empty-state-icon">⚠</div><div class="empty-state-title">Failed to load health data</div><div class="empty-state-desc">${escapeHtml(err.message)}</div></div>`;
+  }
+}
+
+function showAddAgentModal() {
+  showModal('Register New Agent', `
+    <div class="form-group">
+      <label class="form-label">Agent Name *</label>
+      <input id="agentName" class="form-input" placeholder="e.g. claude-code, codex, custom-llm">
+      <div style="font-size:11px;color:var(--text-muted);margin-top:4px">Unique identifier (lowercase, no spaces)</div>
+    </div>
+    <div class="form-group">
+      <label class="form-label">Display Name</label>
+      <input id="agentDisplay" class="form-input" placeholder="e.g. Claude Code">
+    </div>
+    <div class="form-group">
+      <label class="form-label">Description</label>
+      <input id="agentDesc" class="form-input" placeholder="What this agent does">
+    </div>
+    <div class="form-group">
+      <label class="form-label">Agent Type</label>
+      <select id="agentType" class="form-select" onchange="updateAgentForm()">
+        <option value="cli">CLI Binary (local command)</option>
+        <option value="http">HTTP API (remote endpoint)</option>
+        <option value="mcp">MCP Server (Model Context Protocol)</option>
+      </select>
+    </div>
+    <div id="cliFields">
+      <div class="form-group">
+        <label class="form-label">Binary Name *</label>
+        <input id="agentBinary" class="form-input" placeholder="e.g. claude, codex">
+      </div>
+      <div class="form-group">
+        <label class="form-label">Run Arguments (one per line, use {message} for user input)</label>
+        <textarea id="agentRunArgs" class="form-textarea" rows="3" placeholder="claude&#10;-p&#10;{message}"></textarea>
+      </div>
+      <div class="form-group">
+        <label class="form-label">Health Check</label>
+        <select id="agentCheckType" class="form-select">
+          <option value="binary">Binary exists in PATH</option>
+          <option value="custom">Custom command</option>
+        </select>
+      </div>
+      <div class="form-group" id="customCheckGroup" style="display:none">
+        <label class="form-label">Custom Check Command</label>
+        <input id="agentCheckCmd" class="form-input" placeholder="e.g. claude --version">
+      </div>
+    </div>
+    <div id="httpFields" style="display:none">
+      <div class="form-group">
+        <label class="form-label">API URL *</label>
+        <input id="agentApiUrl" class="form-input" placeholder="https://api.example.com/chat">
+      </div>
+      <div class="form-group">
+        <label class="form-label">HTTP Method</label>
+        <select id="agentApiMethod" class="form-select">
+          <option value="POST">POST</option>
+          <option value="GET">GET</option>
+        </select>
+      </div>
+    </div>
+    <div class="form-group">
+      <label class="form-label">Timeout (seconds)</label>
+      <input id="agentTimeout" class="form-input" type="number" value="60">
+    </div>
+    <div class="form-group">
+      <label class="form-label">Router Keywords (comma-separated)</label>
+      <input id="agentKeywords" class="form-input" placeholder="code, debug, test, build">
+      <div style="font-size:11px;color:var(--text-muted);margin-top:4px">Keywords for smart routing to this agent</div>
+    </div>
+  `, `
+    <button class="btn btn-ghost" onclick="closeModal()">Cancel</button>
+    <button class="btn btn-primary" onclick="registerAgent()">Register Agent</button>
+  `);
+
+  // Show/hide custom check command field
+  document.getElementById('agentCheckType').addEventListener('change', (e) => {
+    document.getElementById('customCheckGroup').style.display = e.target.value === 'custom' ? 'block' : 'none';
+  });
+}
+
+function updateAgentForm() {
+  const type = document.getElementById('agentType').value;
+  document.getElementById('cliFields').style.display = type === 'cli' ? 'block' : 'none';
+  document.getElementById('httpFields').style.display = type === 'http' ? 'block' : 'none';
+}
+
+async function registerAgent() {
+  const name = document.getElementById('agentName').value.trim();
+  if (!name) { showToast('Agent name is required', 'error'); return; }
+
+  const type = document.getElementById('agentType').value;
+  const data = {
+    name: name,
+    display_name: document.getElementById('agentDisplay').value.trim() || name,
+    description: document.getElementById('agentDesc').value.trim(),
+    type: type,
+    binary: document.getElementById('agentBinary').value.trim() || name,
+    check_type: document.getElementById('agentCheckType').value === 'custom' ? 'custom' : 'binary',
+    check_command: document.getElementById('agentCheckCmd').value.trim(),
+    timeout: parseInt(document.getElementById('agentTimeout').value) || 60,
+    router_keywords: document.getElementById('agentKeywords').value.split(',').map(k => k.trim()).filter(Boolean),
+  };
+
+  if (type === 'cli') {
+    const runArgs = document.getElementById('agentRunArgs').value.trim();
+    if (runArgs) {
+      data.run_args = runArgs.split('\n').map(a => a.trim()).filter(Boolean);
+    }
+  } else if (type === 'http') {
+    data.api_url = document.getElementById('agentApiUrl').value.trim();
+    data.api_method = document.getElementById('agentApiMethod').value;
+  }
+
+  try {
+    await api.registerAgent(data);
+    closeModal();
+    showToast(`Agent '${name}' registered successfully`, 'success');
+    loadAgents();
+  } catch (err) {
+    showToast(`Error: ${err.message}`, 'error');
+  }
+}
+
+async function removeAgent(name) {
+  if (!confirm(`Remove agent '${name}'?`)) return;
+  try {
+    await api.unregisterAgent(name);
+    showToast(`Agent '${name}' removed`, 'success');
+    loadAgents();
+  } catch (err) {
+    showToast(`Error: ${err.message}`, 'error');
   }
 }

dashboard/pages/agent-time-monitor.html

@@ -0,0 +1,222 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Agentic-OS · Agent Time Monitor</title>
+<style>
+  :root{
+    --bg:#0b0f17; --panel:#121826; --panel2:#0f1420; --line:#1f2a3d;
+    --txt:#e6edf6; --muted:#8a99b3; --accent:#5b8cff; --accent2:#37e0a6;
+    --warn:#ffcf5c; --danger:#ff6b6b;
+    --open:#5b8cff; --hermes:#37e0a6; --gemini:#ffcf5c; --sys:#9b8cff;
+  }
+  *{box-sizing:border-box}
+  body{margin:0;background:var(--bg);color:var(--txt);
+    font-family:"Inter",system-ui,-apple-system,Segoe UI,Roboto,sans-serif;}
+  header{padding:18px 26px;border-bottom:1px solid var(--line);
+    display:flex;align-items:center;justify-content:space-between;flex-wrap:wrap;gap:12px}
+  header h1{font-size:18px;margin:0;font-weight:650;letter-spacing:.2px}
+  header .sub{color:var(--muted);font-size:13px;margin-top:2px}
+  .badge{font-size:11px;color:var(--accent2);border:1px solid #1d3b30;
+    background:#0e1c17;padding:3px 9px;border-radius:20px}
+  main{padding:22px 26px;max-width:1280px;margin:0 auto}
+  .grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(240px,1fr));gap:16px;margin-bottom:22px}
+  .card{background:var(--panel);border:1px solid var(--line);border-radius:14px;padding:18px}
+  .card .label{color:var(--muted);font-size:12px;text-transform:uppercase;letter-spacing:.6px}
+  .card .big{font-size:30px;font-weight:700;margin-top:6px;line-height:1.1}
+  .card .meta{color:var(--muted);font-size:12px;margin-top:6px}
+  .row{display:flex;gap:10px;flex-wrap:wrap;align-items:center;margin:14px 0 8px}
+  button{cursor:pointer;border:1px solid var(--line);background:var(--panel2);
+    color:var(--txt);padding:9px 14px;border-radius:10px;font-size:13px;font-weight:600}
+  button.primary{background:var(--accent);border-color:var(--accent);color:#fff}
+  button:disabled{opacity:.5;cursor:not-allowed}
+  .status{font-size:13px;color:var(--muted)}
+  .status.ok{color:var(--accent2)} .status.err{color:var(--danger)}
+  table{width:100%;border-collapse:collapse;margin-top:6px}
+  th,td{text-align:left;padding:9px 10px;border-bottom:1px solid var(--line);font-size:13px}
+  th{color:var(--muted);font-weight:600;text-transform:uppercase;font-size:11px;letter-spacing:.5px}
+  td.num{text-align:right;font-variant-numeric:tabular-nums}
+  .bar{height:9px;border-radius:6px;background:linear-gradient(90deg,var(--accent),var(--accent2));
+    width:0;transition:width 1s ease-out}
+  .barwrap{background:#0c1320;border-radius:6px;overflow:hidden;min-width:90px}
+  section{background:var(--panel);border:1px solid var(--line);border-radius:14px;
+    padding:16px 18px;margin-bottom:22px}
+  section h2{font-size:14px;margin:0 0 4px;font-weight:650}
+  section .hint{color:var(--muted);font-size:12px;margin-bottom:10px}
+  iframe{border:1px solid var(--line);border-radius:12px;width:100%;height:620px;background:#0a0d14}
+  .pill{display:inline-block;font-size:11px;padding:2px 8px;border-radius:20px;
+    border:1px solid var(--line);color:var(--muted);margin-right:6px}
+  code{background:#0c1320;padding:1px 6px;border-radius:5px;font-size:12px}
+  a{color:var(--accent)}
+</style>
+</head>
+<body>
+<header>
+  <div>
+    <h1>Agentic-OS · Agent Time Monitor</h1>
+    <div class="sub">Total AI-agent time spent on the project · derived from audit &amp; chat logs</div>
+  </div>
+  <div class="badge" id="project-badge">project: agentic-os</div>
+</header>
+
+<main>
+  <section style="background:linear-gradient(135deg,#121826,#0e1626)">
+    <div class="grid">
+      <div class="card">
+        <div class="label">Total Agent Time</div>
+        <div class="big" id="total-time">—</div>
+        <div class="meta" id="total-meta">loading…</div>
+      </div>
+      <div class="card">
+        <div class="label">Agents Active</div>
+        <div class="big" id="agent-count">—</div>
+        <div class="meta" id="agent-meta">distinct agents</div>
+      </div>
+      <div class="card">
+        <div class="label">Logged Events</div>
+        <div class="big" id="event-count">—</div>
+        <div class="meta" id="event-meta">audit + chat + cost</div>
+      </div>
+      <div class="card">
+        <div class="label">Coverage</div>
+        <div class="big" id="coverage">—</div>
+        <div class="meta" id="coverage-meta">first → last activity</div>
+      </div>
+    </div>
+
+    <div class="row">
+      <button class="primary" id="refresh-btn">↻ Recompute</button>
+      <button id="sync-btn">⇪ Sync total to Mnemoverse</button>
+      <span class="status" id="status">Ready. Estimates are session-gap based.</span>
+    </div>
+  </section>
+
+  <section>
+    <h2>Time per Agent</h2>
+    <div class="hint">Each bar is the estimated total time an agent was engaged with the project
+      (sessions of activity within a 30-min gap window, plus a 2-min tail).</div>
+    <table>
+      <thead><tr><th>Agent</th><th>Total Time</th><th style="width:34%">Share</th><th class="num">Sessions</th><th class="num">Touches</th></tr></thead>
+      <tbody id="agent-rows"><tr><td colspan="5" class="meta">loading…</td></tr></tbody>
+    </table>
+  </section>
+
+  <section>
+    <h2>Codebase Knowledge Graph · graphify</h2>
+    <div class="hint">Interactive graphify visualization of the <code>agentic-os</code> codebase
+      (nodes = code symbols/modules, edges = relationships). Rebuild with
+      <code>graphify . --code-only</code> inside the project.</div>
+    <div class="row">
+      <span class="pill" id="g-nodes">nodes: —</span>
+      <span class="pill" id="g-edges">edges: —</span>
+      <span class="pill" id="g-communities">communities: —</span>
+      <a href="/graphify-out/graph.html" target="_blank">↗ open full graph in new tab</a>
+    </div>
+    <iframe src="/graphify-out/graph.html" title="graphify knowledge graph" loading="lazy"></iframe>
+  </section>
+</main>
+
+<script>
+const API = {
+  async get(path){ const r = await fetch(path); return await r.json(); },
+};
+
+function fmtHMS(s){
+  s = Math.floor(s); const h=Math.floor(s/3600), m=Math.floor((s%3600)/60), sec=s%60;
+  return h+"h "+m+"m "+sec+"s";
+}
+function fmtDuration(s){
+  s=Math.floor(s); const h=Math.floor(s/3600), m=Math.floor((s%3600)/60);
+  if(h>0) return h+"h "+m+"m"; return m+"m "+s%60+"s";
+}
+
+async function load(){
+  setStatus("Loading…");
+  try{
+    const data = await API.get("/data/agent-time.json");
+    document.getElementById("total-time").textContent = data.total_human;
+    document.getElementById("total-meta").textContent =
+      "estimated · " + data.method;
+    const agents = data.agents || {};
+    const keys = Object.keys(agents);
+    document.getElementById("agent-count").textContent = keys.length;
+    document.getElementById("event-count").textContent = data.event_count;
+    document.getElementById("coverage").textContent =
+      (data.first_seen||"—").slice(0,10) + " → " + (data.last_seen||"—").slice(0,10);
+
+    // rows
+    const max = Math.max(...keys.map(k=>agents[k].total_seconds), 1);
+    const sorted = keys.sort((a,b)=>agents[b].total_seconds-agents[a].total_seconds);
+    const tb = document.getElementById("agent-rows");
+    tb.innerHTML = "";
+    sorted.forEach((k,i)=>{
+      const a = agents[k];
+      const pct = (a.total_seconds/max*100).toFixed(1);
+      const tr = document.createElement("tr");
+      tr.innerHTML =
+        `<td>${k}</td>`+
+        `<td><b>${fmtDuration(a.total_seconds)}</b></td>`+
+        `<td><div class="barwrap"><div class="bar" data-w="${pct}" style="background:${
+          k==='system'?'var(--sys)':k==='hermes'?'var(--hermes)':k==='opencode'?'var(--open)':k==='gemini'?'var(--gemini)':'linear-gradient(90deg,var(--accent),var(--accent2))'
+        }"></div></div></td>`+
+        `<td class="num">${a.sessions}</td>`+
+        `<td class="num">${a.touches}</td>`;
+      tb.appendChild(tr);
+    });
+    // animate bars
+    setTimeout(()=>document.querySelectorAll(".bar").forEach(b=>b.style.width=b.dataset.w+"%"),60);
+
+    // graph meta
+    if(data.graph){
+      document.getElementById("g-nodes").textContent = "nodes: "+(data.graph.nodes||"—");
+      document.getElementById("g-edges").textContent = "edges: "+(data.graph.edges||"—");
+      document.getElementById("g-communities").textContent = "communities: "+(data.graph.communities||"—");
+    }
+    setStatus("✓ Computed at "+(data.generated_at||"").slice(0,19).replace("T"," ")+" UTC", "ok");
+  }catch(e){
+    setStatus("Failed to load agent-time.json: "+e.message, "err");
+  }
+}
+
+async function recompute(){
+  setStatus("Recomputing from logs…");
+  document.getElementById("refresh-btn").disabled = true;
+  try{
+    const r = await fetch("recompute", {method:"POST"});
+    const j = await r.json();
+    if(!j.ok){ throw new Error(j.error||"recompute failed"); }
+    setStatus("✓ Recomputed: "+j.total_human+" across "+j.agents+" agents", "ok");
+    await load();
+  }catch(e){
+    setStatus("Recompute error: "+e.message, "err");
+  }finally{
+    document.getElementById("refresh-btn").disabled = false;
+  }
+}
+
+async function syncMnemoverse(){
+  const btn = document.getElementById("sync-btn");
+  btn.disabled = true; setStatus("Pushing total to Mnemoverse…");
+  try{
+    const r = await fetch("sync-mnemoverse", {method:"POST"});
+    const j = await r.json();
+    if(j.ok){
+      setStatus("✓ Synced to Mnemoverse: "+j.message, "ok");
+    }else{
+      // graceful: show guidance (no key / offline)
+      setStatus("⚠ Mnemoverse: "+(j.error||"not synced")+(j.hint?(" — "+j.hint):""), "err");
+    }
+  }catch(e){
+    setStatus("Mnemoverse sync error: "+e.message, "err");
+  }finally{ btn.disabled=false; }
+}
+
+function setStatus(msg, cls){ const s=document.getElementById("status"); s.textContent=msg; s.className="status"+(cls?(" "+cls):""); }
+
+document.getElementById("refresh-btn").addEventListener("click", recompute);
+document.getElementById("sync-btn").addEventListener("click", syncMnemoverse);
+load();
+</script>
+</body>
+</html>

dashboard/pages/agent-time.js

@@ -0,0 +1,176 @@
+// Agent Time Monitor page — total time AI agents spent on the project.
+// Data comes from the backend (/api/agent-time), which derives totals
+// from event logs via a session-gap estimator. No Mnemoverse widget.
+
+function fmtDuration(seconds) {
+  seconds = Math.floor(seconds || 0);
+  const h = Math.floor(seconds / 3600);
+  const m = Math.floor((seconds % 3600) / 60);
+  const s = seconds % 60;
+  if (h > 0) return `${h}h ${m}m`;
+  if (m > 0) return `${m}m ${s}s`;
+  return `${s}s`;
+}
+
+function fmtHMS(seconds) {
+  seconds = Math.floor(seconds || 0);
+  const h = Math.floor(seconds / 3600);
+  const m = Math.floor((seconds % 3600) / 60);
+  const s = seconds % 60;
+  return `${h}h ${m}m ${s}s`;
+}
+
+// Agent accent colors, matching agent-health / known identities.
+function agentColor(agent) {
+  const map = {
+    system: 'var(--purple, #9b8cff)',
+    hermes: 'var(--green, #37e0a6)',
+    opencode: 'var(--accent, #6c5ce7)',
+    gemini: 'var(--yellow, #ffcf5c)',
+    codex: '#5b8cff',
+    jarvis: '#ff79c6',
+    kilocode: '#74b9ff',
+    test_claude: '#a29bfe',
+    test: '#7f8fa6',
+  };
+  return map[agent] || 'linear-gradient(90deg, var(--accent), var(--green))';
+}
+
+async function renderAgentTime() {
+  const content = document.getElementById('pageContent');
+  content.innerHTML = `
+    <div class="page-header">
+      <div class="page-header-left">
+        <h1 class="page-title">Agent Time</h1>
+        <p class="page-subtitle">Total time AI agents have spent on this project</p>
+      </div>
+      <div class="btn-group">
+        <button class="btn btn-ghost" onclick="loadAgentTime(false)">↻ Refresh</button>
+        <button class="btn btn-primary" onclick="recomputeAgentTime()">⚡ Recompute</button>
+      </div>
+    </div>
+    <div id="agentTimeBody">
+      <div class="grid grid-4">
+        <div class="card"><div class="skeleton" style="height:90px"></div></div>
+        <div class="card"><div class="skeleton" style="height:90px"></div></div>
+        <div class="card"><div class="skeleton" style="height:90px"></div></div>
+        <div class="card"><div class="skeleton" style="height:90px"></div></div>
+      </div>
+    </div>
+  `;
+  await loadAgentTime(false);
+}
+
+async function loadAgentTime(recompute) {
+  const body = document.getElementById('agentTimeBody');
+  try {
+    const data = await api.getAgentTime(recompute);
+    const agents = data.agents || {};
+    const keys = Object.keys(agents);
+    const max = Math.max(1, ...keys.map(k => agents[k].total_seconds));
+    const sorted = keys.slice().sort((a, b) => agents[b].total_seconds - agents[a].total_seconds);
+
+    const g = data.graph || {};
+    const graphCard = g.nodes != null ? `
+      <div class="card">
+        <div class="card-header"><span class="card-title">Codebase Graph (graphify)</span></div>
+        <div style="display:flex;gap:14px;flex-wrap:wrap;margin-top:8px">
+          <div><div style="font-size:22px;font-weight:700">${g.nodes}</div><div style="font-size:11px;color:var(--text-muted);text-transform:uppercase">nodes</div></div>
+          <div><div style="font-size:22px;font-weight:700">${g.edges}</div><div style="font-size:11px;color:var(--text-muted);text-transform:uppercase">edges</div></div>
+          <div><div style="font-size:22px;font-weight:700">${g.communities != null ? g.communities : '—'}</div><div style="font-size:11px;color:var(--text-muted);text-transform:uppercase">communities</div></div>
+        </div>
+        <a class="btn btn-ghost btn-sm mt-3" href="/dashboard/graphify-out/graph.html" target="_blank">↗ Open interactive graph</a>
+      </div>` : '';
+
+    body.innerHTML = `
+      <div class="grid grid-4">
+        <div class="card">
+          <div class="card-header"><span class="card-title">Total Agent Time</span></div>
+          <div style="font-size:30px;font-weight:800;margin-top:6px">${escapeHtml(data.total_human || '0h 0m 0s')}</div>
+          <div style="font-size:11px;color:var(--text-muted);margin-top:6px">estimated · ${escapeHtml((data.method || '').replace('session-gap estimate ', ''))}</div>
+        </div>
+        <div class="card">
+          <div class="card-header"><span class="card-title">Active Agents</span></div>
+          <div style="font-size:30px;font-weight:800;margin-top:6px">${keys.length}</div>
+          <div style="font-size:11px;color:var(--text-muted);margin-top:6px">distinct agents</div>
+        </div>
+        <div class="card">
+          <div class="card-header"><span class="card-title">Logged Events</span></div>
+          <div style="font-size:30px;font-weight:800;margin-top:6px">${data.event_count || 0}</div>
+          <div style="font-size:11px;color:var(--text-muted);margin-top:6px">audit + chat + cost</div>
+        </div>
+        <div class="card">
+          <div class="card-header"><span class="card-title">Coverage</span></div>
+          <div style="font-size:18px;font-weight:700;margin-top:8px">${(data.first_seen || '—').slice(0, 10)}</div>
+          <div style="font-size:13px;color:var(--text-muted)">→ ${(data.last_seen || '—').slice(0, 10)}</div>
+          <div style="font-size:11px;color:var(--text-muted);margin-top:4px">first → last activity</div>
+        </div>
+      </div>
+
+      <div class="card mt-4">
+        <div class="card-header"><span class="card-title">Time per Agent</span>
+          <span style="font-size:11px;color:var(--text-muted)">sessions of activity (30-min gap) + 2-min tail</span></div>
+        <div class="table-wrap">
+          <table class="agent-table">
+            <thead><tr><th>Agent</th><th>Total Time</th><th>Share</th><th class="num">Sessions</th><th class="num">Touches</th></tr></thead>
+            <tbody>
+              ${sorted.map(k => {
+                const a = agents[k];
+                const pct = ((a.total_seconds / max) * 100).toFixed(1);
+                return `
+                  <tr>
+                    <td><span style="font-weight:600">${escapeHtml(k)}</span></td>
+                    <td><b>${fmtDuration(a.total_seconds)}</b></td>
+                    <td style="min-width:140px">
+                      <div style="height:8px;border-radius:6px;background:var(--bg-elevated,#0c1320);overflow:hidden">
+                        <div style="height:100%;width:0;background:${agentColor(k)};border-radius:6px;transition:width .8s ease-out" data-w="${pct}%"></div>
+                      </div>
+                    </td>
+                    <td class="num">${a.sessions}</td>
+                    <td class="num">${a.touches}</td>
+                  </tr>`;
+              }).join('')}
+            </tbody>
+          </table>
+        </div>
+      </div>
+
+      ${graphCard ? `<div class="card mt-4">${graphCard}</div>` : ''}
+
+      <div style="font-size:11px;color:var(--text-muted);margin-top:14px">
+        Computed ${escapeHtml((data.generated_at || '').replace('T', ' ').slice(0, 19))} UTC.
+        Totals are <b>estimates</b> — the project logs events, not durations; see the method in the report.
+      </div>
+    `;
+    // animate bars
+    setTimeout(() => {
+      document.querySelectorAll('#agentTimeBody [data-w]').forEach(el => { el.style.width = el.dataset.w; });
+    }, 60);
+  } catch (err) {
+    body.innerHTML = `
+      <div class="card">
+        <div class="empty-state">
+          <div class="empty-state-icon">⚠</div>
+          <div class="empty-state-title">Could not load agent-time report</div>
+          <div class="empty-state-desc">${escapeHtml(err.message)}</div>
+          <button class="btn btn-primary mt-3" onclick="recomputeAgentTime()">Recompute now</button>
+        </div>
+      </div>`;
+  }
+}
+
+async function recomputeAgentTime() {
+  const body = document.getElementById('agentTimeBody');
+  showToast('Recomputing from logs…', 'info');
+  try {
+    const res = await api.recomputeAgentTime();
+    if (res.ok) {
+      showToast(`Recomputed: ${res.total_human} across ${res.agents} agents`, 'success');
+      await loadAgentTime(false);
+    } else {
+      showToast('Recompute failed', 'error');
+    }
+  } catch (err) {
+    showToast(`Recompute error: ${err.message}`, 'error');
+  }
+}

dashboard/pages/journal.js

@@ -77,7 +77,8 @@ async function saveJournalEntry() {
     if (wc) wc.textContent = words;
   } catch (err) {
     const status = document.getElementById('journalSaveStatus');
-    if (status) status.textContent = 'Save failed';
+    if (status) status.textContent = 'Save failed: ' + err.message;
+    console.error('Journal save error:', err);
   }
 }
 

dashboard/pages/plugins.js

@@ -4,68 +4,178 @@ async function renderPlugins() {
     <div class="page-header">
       <div class="page-header-left">
         <h1 class="page-title">Plugin Registry</h1>
-        <p class="page-subtitle">Manage installed plugins and extensions</p>
+        <p class="page-subtitle">Install skills from GitHub or create your own</p>
       </div>
-      <button class="btn btn-primary" onclick="showInstallPlugin()">+ Install</button>
+      <button class="btn btn-primary" onclick="showInstallPlugin()">+ Install from GitHub</button>
     </div>
+
+    <div style="display:grid;grid-template-columns:1fr 1fr;gap:16px;margin-bottom:24px">
+      <div class="card">
+        <div class="card-title" style="margin-bottom:12px">Install a Plugin</div>
+        <div class="form-group">
+          <label class="form-label">GitHub Repo URL</label>
+          <input id="pluginRepoInput" class="form-input" placeholder="https://github.com/you/your-skill-repo">
+          <div class="form-hint">Paste a GitHub URL to clone a skill from a repo</div>
+        </div>
+        <div class="form-group">
+          <label class="form-label">Plugin Name (optional)</label>
+          <input id="pluginNameInput" class="form-input" placeholder="auto-detect from repo URL">
+        </div>
+        <button class="btn btn-primary" onclick="installPluginFromRepo()">Install</button>
+        <div id="installStatus" style="margin-top:8px;font-size:12px"></div>
+      </div>
+
+      <div class="card">
+        <div class="card-title" style="margin-bottom:12px">Connect External App</div>
+        <div class="form-group">
+          <label class="form-label">App Name</label>
+          <input id="integrationNameInput" class="form-input" placeholder="e.g., Slack, Zapier, n8n">
+        </div>
+        <div class="form-group">
+          <label class="form-label">Webhook / URL</label>
+          <input id="integrationUrlInput" class="form-input" placeholder="https://hooks.slack.com/...">
+        </div>
+        <div class="form-group">
+          <label class="form-label">Type</label>
+          <select id="integrationType" class="form-input">
+            <option value="webhook">Webhook</option>
+            <option value="api">REST API</option>
+            <option value="zapier">Zapier</option>
+            <option value="n8n">n8n</option>
+          </select>
+        </div>
+        <button class="btn btn-primary" onclick="addIntegration()">Connect</button>
+        <div id="integrationStatus" style="margin-top:8px;font-size:12px"></div>
+      </div>
+    </div>
+
+    <div class="card" style="margin-bottom:16px">
+      <div class="card-title" style="margin-bottom:12px">Connected Apps</div>
+      <div id="integrationsList"></div>
+    </div>
+
     <div id="pluginList"><div class="loading"><div class="loading-spinner"></div></div></div>
   `;
 
   try {
-    const data = await api.getPlugins();
+    const [pluginsData, integrationsData] = await Promise.all([
-    const plugins = data.plugins || [];
+      api.getPlugins(),
-    const container = document.getElementById('pluginList');
+      api.getIntegrations(),
+    ]);
 
-    if (plugins.length === 0) {
+    renderPluginTable(pluginsData.plugins || []);
-      container.innerHTML = '<div class="empty-state"><div class="empty-state-icon">🔌</div><div class="empty-state-title">No plugins installed</div><div class="empty-state-desc">Install plugins from the registry or create your own</div></div>';
+    renderIntegrations(integrationsData.integrations || []);
-      return;
-    }
-
-    container.innerHTML = `
-      <div class="table-wrapper">
-        <table>
-          <thead><tr><th>Plugin</th><th>Version</th><th>Type</th><th>Installed</th></tr></thead>
-          <tbody>
-            ${plugins.map(p => `
-              <tr>
-                <td><strong>${p.name}</strong></td>
-                <td><code>${p.version || '1.0.0'}</code></td>
-                <td><span class="badge badge-info">${p.type || 'skill'}</span></td>
-                <td style="font-size:12px;color:var(--text-muted)">${formatDate(p.installed)}</td>
-              </tr>
-            `).join('')}
-          </tbody>
-        </table>
-      </div>
-      <div style="font-size:12px;color:var(--text-muted);text-align:right;margin-top:8px">${plugins.length} plugin${plugins.length !== 1 ? 's' : ''}</div>
-    `;
   } catch (err) {
     document.getElementById('pluginList').innerHTML = `<div class="empty-state"><div class="empty-state-icon">⚠</div><div class="empty-state-title">${escapeHtml(err.message)}</div></div>`;
   }
 }
 
-function showInstallPlugin() {
+function renderPluginTable(plugins) {
-  showModal('Install Plugin', `
+  const container = document.getElementById('pluginList');
-    <div class="form-group">
+  if (plugins.length === 0) {
-      <label class="form-label">Plugin Name</label>
+    container.innerHTML = '<div class="empty-state"><div class="empty-state-icon">🔌</div><div class="empty-state-title">No plugins installed</div><div class="empty-state-desc">Install plugins from GitHub or create your own</div></div>';
-      <input id="pluginNameInput" class="form-input" placeholder="e.g., my-custom-skill">
+    return;
-      <div class="form-hint">Enter the name of the plugin to install from the registry</div>
+  }
+  container.innerHTML = `
+    <div class="card">
+      <div class="card-title">Installed Plugins (${plugins.length})</div>
+      <div class="table-wrapper">
+        <table>
+          <thead><tr><th>Plugin</th><th>Version</th><th>Type</th><th>Source</th><th>Installed</th><th></th></tr></thead>
+          <tbody>
+            ${plugins.map(p => `
+              <tr>
+                <td><strong>${escapeHtml(p.name)}</strong></td>
+                <td><code>${p.version || '1.0.0'}</code></td>
+                <td><span class="badge badge-info">${p.type || 'skill'}</span></td>
+                <td style="font-size:11px;max-width:200px;overflow:hidden;text-overflow:ellipsis" title="${escapeHtml(p.source || '')}">${escapeHtml(p.source || 'built-in')}</td>
+                <td style="font-size:12px;color:var(--text-muted)">${formatDate(p.installed)}</td>
+                <td>${p.source ? `<button class="btn btn-ghost" style="padding:4px 8px;font-size:11px" onclick="uninstallPlugin('${escapeHtml(p.name)}')">Remove</button>` : '—'}</td>
+              </tr>
+            `).join('')}
+          </tbody>
+        </table>
+      </div>
     </div>
-  `, `
+  `;
-    <button class="btn btn-ghost" onclick="closeModal()">Cancel</button>
-    <button class="btn btn-primary" onclick="installPlugin()">Install</button>
-  `);
 }
 
-async function installPlugin() {
+function renderIntegrations(integrations) {
+  const container = document.getElementById('integrationsList');
+  if (integrations.length === 0) {
+    container.innerHTML = '<div style="font-size:12px;color:var(--text-muted)">No external apps connected yet</div>';
+    return;
+  }
+  container.innerHTML = `<div style="display:flex;flex-direction:column;gap:8px">
+    ${integrations.map(i => `
+      <div style="display:flex;align-items:center;justify-content:space-between;padding:8px 12px;background:var(--bg-secondary);border-radius:6px">
+        <div>
+          <strong style="font-size:13px">${escapeHtml(i.name)}</strong>
+          <span class="badge badge-info" style="margin-left:8px">${escapeHtml(i.type)}</span>
+          <div style="font-size:11px;color:var(--text-muted);margin-top:2px">${escapeHtml(i.url)}</div>
+        </div>
+        <span style="font-size:11px;color:var(--accent)">● connected</span>
+      </div>
+    `).join('')}
+  </div>`;
+}
+
+function showInstallPlugin() {
+  document.getElementById('pluginRepoInput').focus();
+}
+
+async function installPluginFromRepo() {
+  const repoUrl = document.getElementById('pluginRepoInput').value.trim();
   const name = document.getElementById('pluginNameInput').value.trim();
-  if (!name) { showToast('Plugin name required', 'warning'); return; }
+  const statusEl = document.getElementById('installStatus');
+
+  if (!repoUrl) {
+    statusEl.innerHTML = '<span style="color:#ef4444">Please enter a GitHub repo URL</span>';
+    return;
+  }
+
+  statusEl.innerHTML = '<span style="color:var(--accent)">Installing...</span>';
   try {
-    const r = await api.installPlugin(name);
+    const r = await api.installPlugin(name || repoUrl, repoUrl);
-    closeModal();
+    statusEl.innerHTML = `<span style="color:#22c55e">✓ ${escapeHtml(r.plugin)} installed</span>`;
-    showToast(r.status === 'already_installed' ? 'Already installed' : `"${name}" installed`, r.status === 'already_installed' ? 'info' : 'success');
+    document.getElementById('pluginRepoInput').value = '';
+    document.getElementById('pluginNameInput').value = '';
+    setTimeout(() => renderPlugins(), 2000);
+  } catch (err) {
+    statusEl.innerHTML = `<span style="color:#ef4444">Error: ${escapeHtml(err.message)}</span>`;
+  }
+}
+
+async function uninstallPlugin(name) {
+  if (!confirm(`Remove "${name}"?`)) return;
+  try {
+    await api.uninstallPlugin(name);
+    showToast(`${name} removed`, 'success');
     renderPlugins();
   } catch (err) {
     showToast(`Error: ${err.message}`, 'error');
   }
 }
+
+async function addIntegration() {
+  const name = document.getElementById('integrationNameInput').value.trim();
+  const url = document.getElementById('integrationUrlInput').value.trim();
+  const type = document.getElementById('integrationType').value;
+  const statusEl = document.getElementById('integrationStatus');
+
+  if (!name || !url) {
+    statusEl.innerHTML = '<span style="color:#ef4444">Name and URL required</span>';
+    return;
+  }
+
+  statusEl.innerHTML = '<span style="color:var(--accent)">Connecting...</span>';
+  try {
+    const r = await api.addIntegration(name, url, type);
+    statusEl.innerHTML = `<span style="color:#22c55e">✓ ${escapeHtml(r.name)} connected</span>`;
+    document.getElementById('integrationNameInput').value = '';
+    document.getElementById('integrationUrlInput').value = '';
+    setTimeout(() => renderPlugins(), 2000);
+  } catch (err) {
+    statusEl.innerHTML = `<span style="color:#ef4444">Error: ${escapeHtml(err.message)}</span>`;
+  }
+}

dashboard/pages/smart-router.js

@@ -1,3 +1,16 @@
+// Per-agent display metadata (icons + role blurb). Built-ins + known custom agents.
+const ROUTER_AGENT_META = {
+  opencode: { icon: '🔧', blurb: 'Code & DevOps' },
+  hermes:   { icon: '⚡', blurb: 'Memory & Scheduling' },
+  gemini:   { icon: '🧠', blurb: 'Research & Analysis' },
+  jarvis:   { icon: '🤖', blurb: 'Local-first AI / Deep Research' },
+  kilocode: { icon: '💻', blurb: 'AI Coding Assistant' },
+  codex:    { icon: '🧩', blurb: 'Code Generation' },
+};
+function routerAgentMeta(name) {
+  return ROUTER_AGENT_META[name] || { icon: '🤖', blurb: 'Custom agent' };
+}
+
 async function renderSmartRouter() {
   const content = document.getElementById('pageContent');
   content.innerHTML = `
@@ -20,9 +33,7 @@ async function renderSmartRouter() {
           <label class="form-label">Route to Agent</label>
           <select class="form-select" id="routerAgentSelect">
             <option value="auto">🤖 Auto (AI suggests)</option>
-            <option value="opencode">🔧 opencode (Code/DevOps)</option>
+            <!-- agent options injected by loadRouterAgents() -->
-            <option value="hermes">⚡ Hermes (Memory/Scheduling)</option>
-            <option value="gemini">🧠 Gemini CLI (Research/Analysis)</option>
           </select>
         </div>
         <button class="btn btn-primary" onclick="suggestRouter()" style="margin-bottom:16px">🤖 Suggest Agent</button>
@@ -32,14 +43,51 @@ async function renderSmartRouter() {
     <div id="routerResult"></div>
     <div class="section-title" style="margin-top:20px">Routing Rules</div>
     <div class="card">
-      <table>
+      <table id="routerRulesTable">
         <tr><th>Agent</th><th>Best For</th><th>Keywords</th></tr>
-        <tr><td><strong>🔧 opencode</strong></td><td>Code, DevOps, infra, git, file operations</td><td class="text-muted text-sm">code, deploy, git, terraform, docker, test, build, script</td></tr>
+        <!-- rows injected by loadRouterAgents() -->
-        <tr><td><strong>⚡ Hermes</strong></td><td>Memory, scheduling, messaging, skills</td><td class="text-muted text-sm">memory, schedule, cron, reminder, brain, plugin, backup</td></tr>
-        <tr><td><strong>🧠 Gemini CLI</strong></td><td>Research, analysis, study, document, review</td><td class="text-muted text-sm">research, analyze, search, explain, study, learn, report</td></tr>
       </table>
     </div>
   `;
+  await loadRouterAgents();
+}
+
+// Pull the live agent list from the server so the dropdown + rules table
+// always reflect every registered agent (built-in AND custom).
+async function loadRouterAgents() {
+  let agents = [];
+  try {
+    const data = await api.getAgents();
+    agents = (data.agents || []).map(a => a.name);
+  } catch (e) {
+    // Fallback to known built-ins if the API is unreachable.
+    agents = ['opencode', 'hermes', 'gemini'];
+  }
+
+  const select = document.getElementById('routerAgentSelect');
+  const table = document.getElementById('routerRulesTable');
+  if (!select || !table) return;
+
+  // Populate dropdown (preserve the Auto option already in the DOM).
+  agents.forEach(name => {
+    const meta = routerAgentMeta(name);
+    const opt = document.createElement('option');
+    opt.value = name;
+    opt.textContent = `${meta.icon} ${name} (${meta.blurb})`;
+    select.appendChild(opt);
+  });
+
+  // Populate routing-rules table.
+  const rows = agents.map(name => {
+    const meta = routerAgentMeta(name);
+    const kw = (window._routerKeywords && window._routerKeywords[name]) || [];
+    return `<tr>
+      <td><strong>${meta.icon} ${name}</strong></td>
+      <td>${meta.blurb}</td>
+      <td class="text-muted text-sm">${kw.join(', ') || '—'}</td>
+    </tr>`;
+  }).join('');
+  table.innerHTML = `<tr><th>Agent</th><th>Best For</th><th>Keywords</th></tr>${rows}`;
 }
 
 async function suggestRouter() {
@@ -49,8 +97,13 @@ async function suggestRouter() {
   if (btn) { btn.disabled = true; btn.textContent = '⏳ Thinking...'; }
   try {
     const data = await api.suggestRouter(task);
+    // Cache keyword map from scores for the rules table refresh.
+    window._routerKeywords = data.scores ? Object.keys(data.scores).reduce((m, a) => m, {}) : {};
     const result = document.getElementById('routerResult');
-    const agentIcons = { opencode: '🔧', hermes: '⚡', gemini: '🧠' };
+    const agentIcons = {
+      opencode: '🔧', hermes: '⚡', gemini: '🧠',
+      jarvis: '🤖', kilocode: '💻', codex: '🧩'
+    };
     const confidenceColors = { high: 'var(--green)', medium: 'var(--yellow)', low: 'var(--text-muted)' };
     result.innerHTML = `
       <div class="card" style="border-color:${confidenceColors[data.confidence] || 'var(--border)'};margin-bottom:12px">

dashboard/pages/terminal.js

@@ -0,0 +1,150 @@
+async function renderTerminal() {
+  const content = document.getElementById('pageContent');
+  content.innerHTML = `
+    <div class="page-header">
+      <div class="page-header-left">
+        <h1 class="page-title">Terminal</h1>
+        <p class="page-subtitle">Full bash shell in the browser — WSL environment</p>
+      </div>
+      <div class="btn-group">
+        <button class="btn btn-ghost" onclick="terminalReconnect()">↻ Reconnect</button>
+        <button class="btn btn-ghost" onclick="terminalClear()">✕ Clear</button>
+        <span id="terminalStatus" class="nav-badge" style="background:var(--yellow)">Connecting...</span>
+      </div>
+    </div>
+    <div class="terminal-container">
+      <div id="terminal"></div>
+    </div>
+  `;
+
+  // Load xterm.js from CDN (with fallback)
+  try {
+    await loadScript('https://cdn.jsdelivr.net/npm/xterm@5.3.0/lib/xterm.min.js');
+    await loadScript('https://cdn.jsdelivr.net/npm/xterm-addon-fit@0.8.0/lib/xterm-addon-fit.js');
+  } catch (err) {
+    // Fallback to unpkg
+    await loadScript('https://unpkg.com/xterm@5.3.0/lib/xterm.min.js');
+    await loadScript('https://unpkg.com/xterm-addon-fit@0.8.0/lib/xterm-addon-fit.js');
+  }
+
+  // Verify Terminal and FitAddon are available
+  if (typeof Terminal === 'undefined') {
+    throw new Error('xterm.js failed to load from CDN');
+  }
+
+  // Initialize terminal
+  const term = new Terminal({
+    cursorBlink: true,
+    fontSize: 14,
+    fontFamily: "'JetBrains Mono', 'Fira Code', 'Cascadia Code', 'Courier New', monospace",
+    theme: {
+      background: '#0d1117',
+      foreground: '#c9d1d9',
+      cursor: '#58a6ff',
+      selection: '#264f78',
+      black: '#0d1117',
+      red: '#ff7b72',
+      green: '#3fb950',
+      yellow: '#d29922',
+      blue: '#58a6ff',
+      magenta: '#bc8cff',
+      cyan: '#39d2c0',
+      white: '#c9d1d9',
+    },
+    scrollback: 50000,
+    allowProposedApi: true,
+    convertEol: true,
+  });
+
+  const FitAddonClass = window.FitAddon?.FitAddon || window.FitAddon;
+  if (!FitAddonClass) {
+    throw new Error('xterm FitAddon failed to load');
+  }
+  const fitAddon = new FitAddonClass();
+  term.loadAddon(fitAddon);
+  term.open(document.getElementById('terminal'));
+  fitAddon.fit();
+
+  window._agenticTerm = term;
+  window._agenticFit = fitAddon;
+
+  // Connect WebSocket
+  const protocol = window.location.protocol === 'https:' ? 'wss:' : 'ws:';
+  const wsPort = 8082;
+  const wsUrl = `${protocol}//${window.location.hostname}:${wsPort}`;
+  const statusEl = document.getElementById('terminalStatus');
+
+  try {
+    const ws = new WebSocket(wsUrl);
+    window._agenticWs = ws;
+
+    ws.onopen = () => {
+      statusEl.textContent = 'Connected';
+      statusEl.style.background = 'var(--green)';
+      term.writeln('\x1b[32m✓ Connected to Agentic OS terminal\x1b[0m');
+      term.writeln(`\x1b[90m  WSL • ${navigator.userAgent.includes('Windows') ? 'Windows browser → WSL shell' : 'Linux shell'}\x1b[0m\r\n`);
+      ws.send(JSON.stringify({ action: 'resize', cols: term.cols, rows: term.rows }));
+    };
+
+    ws.onmessage = (event) => {
+      if (typeof event.data === 'string') {
+        term.write(event.data);
+      }
+    };
+
+    ws.onclose = () => {
+      statusEl.textContent = 'Disconnected';
+      statusEl.style.background = 'var(--red)';
+      term.writeln('\r\n\x1b[31m✕ Connection closed\x1b[0m');
+    };
+
+    ws.onerror = () => {
+      statusEl.textContent = 'Error';
+      statusEl.style.background = 'var(--red)';
+    };
+
+    // Send input
+    term.onData((data) => {
+      if (ws.readyState === WebSocket.OPEN) {
+        ws.send(JSON.stringify({ action: 'input', data: data }));
+      }
+    });
+
+    // Resize handler with debounce
+    let resizeTimeout;
+    const resizeObserver = new ResizeObserver(() => {
+      clearTimeout(resizeTimeout);
+      resizeTimeout = setTimeout(() => {
+        fitAddon.fit();
+        if (ws.readyState === WebSocket.OPEN) {
+          ws.send(JSON.stringify({ action: 'resize', cols: term.cols, rows: term.rows }));
+        }
+      }, 100);
+    });
+    resizeObserver.observe(document.getElementById('terminal'));
+    window._agenticResize = resizeObserver;
+
+  } catch (err) {
+    statusEl.textContent = 'Failed';
+    statusEl.style.background = 'var(--red)';
+    term.writeln(`\x1b[31mError: ${err.message}\x1b[0m`);
+  }
+
+  term.focus();
+}
+
+function terminalReconnect() {
+  if (window._agenticWs) window._agenticWs.close();
+  if (window._agenticResize) window._agenticResize.disconnect();
+  renderTerminal();
+}
+
+function terminalClear() {
+  if (window._agenticTerm) {
+    window._agenticTerm.clear();
+    // Also send clear escape sequence to PTY
+    if (window._agenticWs && window._agenticWs.readyState === WebSocket.OPEN) {
+      window._agenticWs.send(JSON.stringify({ action: 'input', data: '\x0c' }));
+    }
+  }
+}

dashboard/serve_monitor.py

@@ -0,0 +1,163 @@
+#!/usr/bin/env python3
+"""
+Agentic-OS :: Localhost Agent-Time Monitor Server
+-------------------------------------------------
+Stdlib-only HTTP server (no pip deps) that serves the project folder on
+localhost and exposes two action endpoints:
+
+  GET  /                          -> redirects to the monitor dashboard
+  GET  /dashboard/pages/agent-time-monitor.html  -> the dashboard
+  GET  /agent-time.json           -> computed total-agent-time report
+  GET  /graphify-out/graph.html   -> graphify code knowledge graph
+  POST /recompute                 -> re-run the time analyzer, return summary
+  POST /sync-mnemoverse           -> push total time to Mnemoverse (graceful)
+
+Run:  python3 dashboard/serve_monitor.py [--port 8765]
+Then open:  http://localhost:8765/dashboard/pages/agent-time-monitor.html
+"""
+import json
+import os
+import subprocess
+import sys
+import urllib.request
+import urllib.error
+from http.server import SimpleHTTPRequestHandler, ThreadingHTTPServer
+from functools import partial
+
+ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))  # agentic-os/
+ANALYZER = os.path.join(ROOT, "scripts", "analyze_agent_time.py")
+AGENT_TIME = os.path.join(ROOT, "data", "agent-time.json")
+MNEMOVERSE_URL = "https://core.mnemoverse.com/api/v1/memory/write"
+DASHBOARD = "/dashboard/pages/agent-time-monitor.html"
+DEFAULT_PORT = int(os.environ.get("MONITOR_PORT", "8765"))
+
+
+def run_analyzer():
+    """Recompute agent-time.json. Returns (ok, summary_dict)."""
+    try:
+        proc = subprocess.run(
+            [sys.executable, ANALYZER],
+            cwd=ROOT, capture_output=True, text=True, timeout=120,
+        )
+        if proc.returncode != 0:
+            return False, {"error": proc.stderr.strip() or "analyzer exited non-zero"}
+        with open(AGENT_TIME, "r", encoding="utf-8") as f:
+            data = json.load(f)
+        return True, {
+            "total_seconds": data["total_seconds"],
+            "total_human": data["total_human"],
+            "agents": len(data.get("agents", {})),
+            "events": data.get("event_count", 0),
+        }
+    except Exception as e:
+        return False, {"error": str(e)}
+
+
+def sync_mnemoverse(api_key=None):
+    """Write the total agent time to Mnemoverse. Graceful on missing key/offline."""
+    api_key = api_key or os.environ.get("MNEMOVERSE_API_KEY", "")
+    if not api_key:
+        return False, {
+            "error": "no MNEMOVERSE_API_KEY set",
+            "hint": "export MNEMOVERSE_API_KEY=mk_live_... then click again",
+        }
+    try:
+        with open(AGENT_TIME, "r", encoding="utf-8") as f:
+            data = json.load(f)
+    except Exception as e:
+        return False, {"error": "cannot read agent-time.json: " + str(e)}
+
+    content = (
+        f"Agentic-OS total AI-agent time on project: {data['total_human']} "
+        f"across {len(data.get('agents', {}))} agents "
+        f"({data.get('event_count', 0)} logged events). "
+        f"Method: {data.get('method')}. Last computed {data.get('generated_at')}."
+    )
+    payload = json.dumps({
+        "content": content,
+        "concepts": ["agentic-os", "agent-time", "agentic-metrics", "ai-agent-usage"],
+        "domain": "agentic-os",
+    }).encode("utf-8")
+    req = urllib.request.Request(
+        MNEMOVERSE_URL, data=payload, method="POST",
+        headers={"Content-Type": "application/json", "X-Api-Key": api_key},
+    )
+    try:
+        with urllib.request.urlopen(req, timeout=20) as resp:
+            body = resp.read().decode("utf-8", "replace")
+            try:
+                j = json.loads(body)
+            except Exception:
+                j = {"raw": body[:200]}
+            return True, {"message": "memory written to Mnemoverse", "response": j}
+    except urllib.error.HTTPError as e:
+        return False, {"error": f"HTTP {e.code}: {e.read().decode('utf-8','replace')[:200]}"}
+    except urllib.error.URLError as e:
+        return False, {"error": "network error: " + str(e.reason),
+                       "hint": "Mnemoverse unreachable from this host"}
+
+
+class Handler(SimpleHTTPRequestHandler):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, directory=ROOT, **kwargs)
+
+    def _send_json(self, obj, code=200):
+        body = json.dumps(obj).encode("utf-8")
+        self.send_response(code)
+        self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(body)))
+        self.send_header("Access-Control-Allow-Origin", "*")
+        self.end_headers()
+        self.wfile.write(body)
+
+    def do_GET(self):
+        if self.path in ("/", "/index.html"):
+            self.send_response(302)
+            self.send_header("Location", DASHBOARD)
+            self.end_headers()
+            return
+        # Default: serve files from ROOT (html, json, graph.html, etc.)
+        super().do_GET()
+
+    def do_POST(self):
+        if self.path == "/recompute":
+            ok, summary = run_analyzer()
+            self._send_json({"ok": ok, **summary}, 200 if ok else 500)
+            return
+        if self.path == "/sync-mnemoverse":
+            ok, result = sync_mnemoverse()
+            self._send_json({"ok": ok, **result}, 200 if ok else 200)
+            return
+        self._send_json({"ok": False, "error": "unknown endpoint"}, 404)
+
+    def log_message(self, fmt, *args):
+        sys.stderr.write("[monitor] " + (fmt % args) + "\n")
+
+
+def main():
+    import argparse
+    p = argparse.ArgumentParser()
+    p.add_argument("--port", type=int, default=DEFAULT_PORT)
+    p.add_argument("--host", default="127.0.0.1")
+    args = p.parse_args()
+
+    # ensure a fresh agent-time.json exists
+    if not os.path.exists(AGENT_TIME):
+        ok, s = run_analyzer()
+        print(("recompute ok" if ok else "recompute failed: " + str(s)))
+
+    httpd = ThreadingHTTPServer((args.host, args.port), Handler)
+    url = f"http://{args.host}:{args.port}{DASHBOARD}"
+    print("Agentic-OS Agent-Time Monitor")
+    print(f"  serving : {ROOT}")
+    print(f"  dashboard: {url}")
+    print(f"  mnemoverse: {'ENABLED (key set)' if os.environ.get('MNEMOVERSE_API_KEY') else 'disabled (set MNEMOVERSE_API_KEY to enable sync)'}")
+    print("  ctrl-c to stop")
+    try:
+        httpd.serve_forever()
+    except KeyboardInterrupt:
+        print("\nstopped.")
+
+
+if __name__ == "__main__":
+    main()

dashboard/start-monitor.sh

@@ -0,0 +1,10 @@
+#!/usr/bin/env bash
+# Start the Agentic-OS Agent-Time Monitor on localhost.
+# Usage:  ./dashboard/start-monitor.sh [port]
+# Then open: http://localhost:<port>/dashboard/pages/agent-time-monitor.html
+set -e
+cd "$(dirname "$0")/.."
+PORT="${1:-8765}"
+if [ -d venv ]; then . venv/bin/activate; fi
+echo "Starting monitor on http://127.0.0.1:${PORT} ..."
+exec python3 dashboard/serve_monitor.py --port "${PORT}"

dashboard/styles.css

@@ -1,3 +1,74 @@
+/* ─── Terminal ─────────────────────────────────────────────────── */
+.terminal-container {
+  background: #0d1117;
+  border: 1px solid var(--border);
+  border-radius: 12px;
+  overflow: hidden;
+  height: calc(100vh - 180px);
+  min-height: 400px;
+  position: relative;
+}
+
+#terminal {
+  width: 100%;
+  height: 100%;
+  padding: 8px;
+}
+
+#terminal .xterm {
+  height: 100%;
+}
+
+#terminal .xterm-viewport {
+  overflow-y: auto !important;
+}
+
+/* ─── Agent Cards ──────────────────────────────────────────────── */
+.agent-card {
+  transition: border-color 0.2s, box-shadow 0.2s;
+}
+.agent-card:hover {
+  border-color: var(--accent);
+  box-shadow: 0 0 0 1px var(--accent-glow);
+}
+.agent-card-header {
+  display: flex;
+  align-items: center;
+  gap: 8px;
+}
+
+.agent-table {
+  width: 100%;
+  border-collapse: collapse;
+}
+.agent-table th {
+  text-align: left;
+  padding: 10px 12px;
+  font-size: 11px;
+  text-transform: uppercase;
+  color: var(--text-muted);
+  border-bottom: 1px solid var(--border);
+}
+.agent-table td {
+  padding: 10px 12px;
+  border-bottom: 1px solid var(--border);
+  font-size: 13px;
+}
+.agent-table tr:last-child td {
+  border-bottom: none;
+}
+.agent-table tr:hover td {
+  background: var(--bg-card-hover);
+}
+
+.btn-sm {
+  padding: 4px 10px;
+  font-size: 11px;
+}
+.mt-4 {
+  margin-top: 16px;
+}
+
 :root {
   --bg-primary: #0d1117;
   --bg-secondary: #151b24;

dashboard/test.html

@@ -0,0 +1,20 @@
+<!DOCTYPE html>
+<html>
+<head><title>Agentic OS Test</title></head>
+<body>
+<h1>Connection Test</h1>
+<div id="status">Testing...</div>
+<div id="result"></div>
+<script>
+fetch('/api/status')
+  .then(r => r.json())
+  .then(d => {
+    document.getElementById('status').textContent = 'SUCCESS: API reachable';
+    document.getElementById('result').textContent = JSON.stringify(d, null, 2);
+  })
+  .catch(e => {
+    document.getElementById('status').textContent = 'FAILED: ' + e.message;
+  });
+</script>
+</body>
+</html>

dashboard/utils.js

@@ -111,6 +111,7 @@ function renderSkeleton(count = 3) {
 
 const PAGE_TITLES = {
   dashboard: { title: 'Dashboard', breadcrumb: 'Overview' },
+  terminal: { title: 'Terminal', breadcrumb: 'Browser-based shell' },
   skills: { title: 'Skills Hub', breadcrumb: 'Browse & execute skills' },
   memory: { title: 'Memory', breadcrumb: 'Shared brain context' },
   scheduler: { title: 'Scheduler', breadcrumb: 'Automated workflows' },
@@ -130,4 +131,5 @@ const PAGE_TITLES = {
   'smart-router': { title: 'Smart Router', breadcrumb: 'Task routing intelligence' },
   'learning-analytics': { title: 'Learning Analytics', breadcrumb: 'Skill improvement tracking' },
   'session-replay': { title: 'Session Replay', breadcrumb: 'Conversation history playback' },
+  'agent-time': { title: 'Agent Time', breadcrumb: 'Total agent effort on this project' },
 };

data/agent-registry.json

@@ -0,0 +1,47 @@
+{
+  "jarvis": {
+    "name": "jarvis",
+    "display_name": "OpenJarvis",
+    "description": "Local-first personal AI: deep research, knowledge, memory, general reasoning",
+    "binary": "jarvis-ask",
+    "type": "cli",
+    "run_args": [
+      "jarvis-ask",
+      "{message}"
+    ],
+    "check_type": "binary",
+    "timeout": 120,
+    "builtin": false,
+    "api_method": "POST"
+  },
+  "kilocode": {
+    "name": "kilocode",
+    "display_name": "Kilo Code",
+    "description": "AI coding assistant by Kilo (linux binary via wrapper)",
+    "binary": "kilocode",
+    "type": "cli",
+    "run_args": [
+      "kilocode",
+      "{message}"
+    ],
+    "check_type": "binary",
+    "timeout": 120,
+    "builtin": false,
+    "api_method": "POST"
+  },
+  "codex": {
+    "name": "codex",
+    "display_name": "OpenAI Codex",
+    "description": "OpenAI Codex coding/execution agent",
+    "binary": "codex",
+    "type": "cli",
+    "run_args": [
+      "codex",
+      "{message}"
+    ],
+    "check_type": "binary",
+    "timeout": 300,
+    "builtin": false,
+    "api_method": "POST"
+  }
+}

data/agent-stats.json

@@ -0,0 +1 @@
+{}

data/agent-time.json

@@ -0,0 +1,83 @@
+{
+  "project": "agentic-os",
+  "generated_at": "2026-07-25T18:27:15.982570+00:00",
+  "method": "session-gap estimate (GAP=1800s, TAIL=120s)",
+  "graph": {
+    "nodes": 321,
+    "edges": 517,
+    "communities": 41,
+    "file": "graphify-out/graph.json"
+  },
+  "gap_seconds": 1800,
+  "tail_seconds": 120,
+  "total_seconds": 20568,
+  "total_human": "5h 42m 48s",
+  "agents": {
+    "opencode": {
+      "sessions": 8,
+      "touches": 42,
+      "total_seconds": 4566,
+      "first_seen": "2026-06-23T11:17:40.771655+00:00",
+      "last_seen": "2026-07-25T17:40:45.570834+00:00"
+    },
+    "system": {
+      "sessions": 12,
+      "touches": 114,
+      "total_seconds": 7374,
+      "first_seen": "2026-06-25T17:58:22.902546+00:00",
+      "last_seen": "2026-07-25T17:10:23.236024+00:00"
+    },
+    "hermes": {
+      "sessions": 9,
+      "touches": 36,
+      "total_seconds": 6808,
+      "first_seen": "2026-06-26T01:25:01.320339+00:00",
+      "last_seen": "2026-07-25T17:42:17.726478+00:00"
+    },
+    "gemini": {
+      "sessions": 1,
+      "touches": 3,
+      "total_seconds": 220,
+      "first_seen": "2026-06-28T17:26:01.078648+00:00",
+      "last_seen": "2026-06-28T17:27:41.105686+00:00"
+    },
+    "test_claude": {
+      "sessions": 1,
+      "touches": 2,
+      "total_seconds": 129,
+      "first_seen": "2026-06-28T17:47:56.773101+00:00",
+      "last_seen": "2026-06-28T17:48:05.984878+00:00"
+    },
+    "jarvis": {
+      "sessions": 2,
+      "touches": 3,
+      "total_seconds": 240,
+      "first_seen": "2026-06-28T20:44:32.727658+00:00",
+      "last_seen": "2026-07-17T17:30:21.986571+00:00"
+    },
+    "kilocode": {
+      "sessions": 2,
+      "touches": 3,
+      "total_seconds": 240,
+      "first_seen": "2026-06-28T20:44:32.730628+00:00",
+      "last_seen": "2026-07-17T17:30:21.988722+00:00"
+    },
+    "test": {
+      "sessions": 1,
+      "touches": 1,
+      "total_seconds": 120,
+      "first_seen": "2026-06-28T21:39:14.911119+00:00",
+      "last_seen": "2026-06-28T21:39:14.911119+00:00"
+    },
+    "codex": {
+      "sessions": 1,
+      "touches": 3,
+      "total_seconds": 871,
+      "first_seen": "2026-07-17T17:18:53.396385+00:00",
+      "last_seen": "2026-07-17T17:31:24.434628+00:00"
+    }
+  },
+  "event_count": 207,
+  "first_seen": "2026-06-23T11:17:40.771655+00:00",
+  "last_seen": "2026-07-25T17:42:17.726478+00:00"
+}

data/goals.json

@@ -1,13 +1,13 @@
 [
   {
-    "id": "c1c992ef",
+    "id": "2c4b22ac",
-    "title": "Test goal",
+    "title": "Push everything in the Kanban board down the line",
-    "description": "",
+    "description": "It involves different skills to get different things done.",
-    "category": "development",
+    "category": "general",
-    "target_date": "",
+    "target_date": "2026-06-28",
     "status": "active",
-    "progress": 0,
+    "progress": 50,
-    "created": "2026-06-05T09:50:30.334519+00:00",
+    "created": "2026-06-28T21:48:06.763421+00:00",
-    "updated": "2026-06-05T09:50:30.334541+00:00"
+    "updated": "2026-06-28T21:48:13.383386+00:00"
   }
 ]

data/integrations.json

@@ -0,0 +1,11 @@
+{
+  "integrations": [
+    {
+      "name": "test-webhook",
+      "url": "https://example.com/hook",
+      "type": "webhook",
+      "added": "2026-06-28T17:18:11.253089+00:00",
+      "status": "active"
+    }
+  ]
+}

data/kanban/0f822987.json

@@ -2,11 +2,11 @@
   "id": "0f822987",
   "title": "Fix login bug",
   "body": "The login page has a race condition",
-  "status": "todo",
+  "status": "done",
   "priority": "high",
   "assignee": "opencode",
   "comments": [],
   "links": [],
   "created": "2026-06-05T09:52:18.236452+00:00",
-  "updated": "2026-06-05T09:52:18.236473+00:00"
+  "updated": "2026-07-17T16:54:37.061957+00:00"
 }

data/kanban/1314316c.json

@@ -0,0 +1,12 @@
+{
+  "id": "1314316c",
+  "title": "AT",
+  "body": "",
+  "status": "triage",
+  "priority": "medium",
+  "assignee": "",
+  "comments": [],
+  "links": [],
+  "created": "2026-07-17T07:51:37.997814+00:00",
+  "updated": "2026-07-17T16:02:48.789421+00:00"
+}

data/kanban/7a250df7.json

@@ -0,0 +1,12 @@
+{
+  "id": "7a250df7",
+  "title": "Login to get gemini running",
+  "body": "login to google so gemini will be running in this os",
+  "status": "done",
+  "priority": "high",
+  "assignee": "hermes",
+  "comments": [],
+  "links": [],
+  "created": "2026-06-26T01:30:00.162737+00:00",
+  "updated": "2026-07-17T16:54:35.405173+00:00"
+}

data/kanban/8893ad14.json

@@ -2,13 +2,13 @@
   "id": "8893ad14",
   "title": "Test kanban task",
   "body": "",
-  "status": "blocked",
+  "status": "done",
   "priority": "medium",
   "assignee": "",
   "comments": [],
   "links": [],
   "created": "2026-06-05T09:50:30.293643+00:00",
-  "updated": "2026-06-05T09:52:18.274595+00:00",
+  "updated": "2026-07-17T17:19:04.258650+00:00",
   "summary": "Test done",
   "completed_at": "2026-06-05T09:50:46.473612+00:00",
   "block_reason": "Waiting for API review"

data/router-keywords.json

@@ -0,0 +1,29 @@
+{
+  "jarvis": [
+    "jarvis",
+    "research",
+    "deep-research",
+    "knowledge",
+    "memory",
+    "reasoning",
+    "local"
+  ],
+  "kilocode": [
+    "kilo",
+    "kilocode",
+    "code",
+    "coding",
+    "programming",
+    "refactor",
+    "implement"
+  ],
+  "codex": [
+    "codex",
+    "code",
+    "debug",
+    "test",
+    "build",
+    "fix",
+    "implement"
+  ]
+}

docs/GRAPHIFY_MEMORY.md

@@ -0,0 +1,58 @@
+# Agentic-OS memory layer + Graphify — honest status
+
+## Can Graphify BE the memory layer?
+**Partially, and not as a replacement for the write path.**
+
+What Graphify is: a tool that turns a *codebase* into a knowledge graph
+(nodes = code symbols/modules, edges = relationships) and lets you
+visualize / query it. It is a **read/visualize/query layer over your
+files** — it does NOT store or write memory. The OS's actual
+memory write path stays `brain/memory.md`, `append_audit()`,
+`data/*.json`, etc.
+
+## What we verified (2026-07-25)
+- `graphify . --code-only` over the whole project → **321 nodes, 517
+  edges, 41 communities** (graphify-out/graph.json + graph.html).
+  This graphs the *code* (server.py, skills' .py, etc.).
+- `graphify brain skills --code-only` → **0 nodes**. The memory
+  folders are almost entirely **Markdown**, which `--code-only`
+  skips. So the memory *content* is invisible to a code-only build.
+- To graph the *memory docs* (markdown notes), Graphify needs an
+  LLM key for semantic extraction (GEMINI_API_KEY / GOOGLE_API_KEY
+  / ANTHROPIC_API_KEY / OPENAI_API_KEY / DEEPSEEK_API_KEY /
+  MOONSHOT_API_KEY). With a key:
+  `graphify brain skills` (no --code-only) will build a graph that
+  includes your notes as nodes. Without a key it errors out.
+
+## Recommended setup (works today, upgrades with a key)
+1. Build the code graph (no key needed):
+     cd ~/agentic-os && graphify . --code-only
+   → live in the dashboard at http://localhost:8080/graphify-out/graph.html
+     and the "Agent Time" page's "Open interactive graph" link.
+2. (Optional, with a key) Build the memory-inclusive graph:
+     export GEMINI_API_KEY=...
+     graphify brain skills data            # docs + code, semantic
+   This adds your memory notes as queryable nodes.
+3. Expose it to the OS agents as a query tool (MCP or HTTP):
+     # HTTP (team/shared):
+     python -m graphify.serve graphify-out/graph.json --transport http --port 8081
+     # or stdio MCP for a single agent:
+     python -m graphify.serve graphify-out/graph.json
+   Then point the agent/MCP client at it. Agents can ASK the graph
+   ("what connects memory-consolidation to audit?", "show the
+   agentic-os data flow") — a retrieval aid, not a memory writer.
+
+## Bottom line
+- ✅ Use Graphify as a **visualization + semantic-query layer** for the
+  OS's memory/code. Great for "what's in my brain and how does it
+  connect."
+- ❌ Do NOT treat it as the memory store. Writing memory still goes
+  through the existing `brain/` + `audit` + `data/` files. Graphify
+  reads those; it never writes them.
+- ⚠️ Memory-note graphing requires an LLM key; code graphing does not.
+
+## Files
+- graphify-out/        — built code graph (graph.json, graph.html, GRAPH_REPORT.md)
+- scripts/analyze_agent_time.py — agent-time estimator (the dashboard's data source)
+- dashboard/.../agent-time.js    — integrated "Agent Time" page (port 8080)
+- dashboard/serve_monitor.py      — standalone monitor (kept, unused by integration)

docs/README.md

@@ -0,0 +1,636 @@
+# Agentic OS — Documentation
+
+> Multi-agent orchestration platform — FastAPI backend + vanilla JS SPA dashboard
+> Version: 1.3.0 | Last updated: 2026-06-28
+
+## Table of Contents
+
+1. [Quick Start](#quick-start)
+2. [Architecture Overview](#architecture-overview)
+3. [Dashboard Pages](#dashboard-pages)
+4. [Web Terminal](#web-terminal)
+5. [Agent System](#agent-system)
+6. [API Reference](#api-reference)
+7. [Skills](#skills)
+8. [Scheduler](#scheduler)
+9. [Configuration](#configuration)
+10. [Development Guide](#development-guide)
+
+---
+
+## Quick Start
+
+```bash
+# Start the server
+cd ~/agentic-os
+./start.sh
+
+# Or with browser auto-open
+./start.sh --open
+
+# Check status
+./start.sh --status
+
+# Stop
+./start.sh --stop
+```
+
+**URLs:**
+- Dashboard: `http://127.0.0.1:8081`
+- Web Terminal: `http://127.0.0.1:8082` (WebSocket)
+- API Base: `http://127.0.0.1:8081/api/`
+
+---
+
+## Architecture Overview
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│                    AGENTIC OS DASHBOARD                      │
+│                   (FastAPI + Vanilla JS SPA)                 │
+├─────────────────────────────────────────────────────────────┤
+│                                                              │
+│  ┌─────────┐  ┌──────────┐  ┌───────────┐  ┌───────────┐  │
+│  │ opencode │  │  Hermes   │  │  Gemini   │  │  Custom   │  │
+│  │  (Code)  │  │ (Memory)  │  │(Research) │  │  Agents   │  │
+│  └────┬─────┘  └─────┬─────┘  └─────┬─────┘  └─────┬─────┘  │
+│       │              │              │              │         │
+│  ─────┴──────────────┴──────────────┴──────────────┴──────── │
+│                        Agent Router                          │
+│  ─────────────────────────────────────────────────────────── │
+│                     FastAPI Backend                          │
+│  ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐ ┌──────────┐ │
+│  │ Brain  │ │Skills  │ │Kanban  │ │Journal │ │ Terminal │ │
+│  │ (files)│ │(agents)│ │(JSON)  │ │(files) │ │  (PTY)   │ │
+│  └────────┘ └────────┘ └────────┘ └────────┘ └──────────┘ │
+└─────────────────────────────────────────────────────────────┘
+```
+
+**Tech Stack:**
+- Backend: Python 3.11+, FastAPI, Uvicorn
+- Frontend: Vanilla JS, Chart.js, xterm.js
+- Terminal: WebSocket + PTY (pseudo-terminal)
+- Data: JSON files (no database required)
+- Agents: CLI binaries (opencode, hermes, gemini, + custom)
+
+---
+
+## Dashboard Pages
+
+| Page | Route | Description |
+|------|-------|-------------|
+| Dashboard | `#dashboard` | System overview, agent status, recent activity |
+| AI Chat | `#chat` | Multi-agent chat terminal |
+| Terminal | `#terminal` | Browser-based bash shell (xterm.js) |
+| Skills | `#skills` | Browse and execute 17+ skills |
+| Memory | `#memory` | Shared brain context files |
+| Scheduler | `#scheduler` | Cron job management |
+| Audit | `#audit` | System activity trail |
+| Kanban | `#kanban` | 6-column task board |
+| Goals | `#goals` | Project targets with progress tracking |
+| Journal | `#journal` | Daily entries with search |
+| Agent Health | `#agent-health` | Agent monitoring + registration |
+| Smart Router | `#smart-router` | Task routing intelligence |
+| Learning Analytics | `#learning-analytics` | Skill eval scores and trends |
+| Session Replay | `#session-replay` | Conversation history playback |
+| Cost Analytics | `#cost` | Token usage and spending |
+| Plugins | `#plugins` | Plugin registry management |
+| Backups | `#backups` | Backup/restore system |
+| Prompts | `#prompts` | Reusable prompt templates |
+| Standards | `#standards` | Project conventions |
+| Settings | `#settings` | System configuration |
+| Setup Wizard | `#setup-wizard` | Guided configuration |
+
+---
+
+## Web Terminal
+
+The terminal provides a full bash shell in the browser using xterm.js connected to a PTY via WebSocket.
+
+**How it works:**
+1. Server forks a PTY (`pty.fork()`) running `/bin/bash`
+2. WebSocket server on port 8082 relays I/O between browser and PTY
+3. xterm.js renders the terminal with 256-color support
+4. Resize events propagate via `ioctl(TIOCSWINSZ)`
+
+**Features:**
+- Full bash shell with tab completion, history, colors
+- Automatic terminal resizing
+- 10,000 line scrollback
+- Reconnect button if connection drops
+- Dark theme matching dashboard
+
+**Security:** The terminal runs as the server process user. Only accessible from localhost by default.
+
+---
+
+## Agent System
+
+### Built-in Agents
+
+| Agent | Binary | Role | Check Method |
+|-------|--------|------|--------------|
+| OpenCode | `opencode` | Code generation, DevOps, file ops | Binary in PATH |
+| Hermes Agent | `hermes` | Memory, scheduling, coordination | Binary in PATH |
+| Gemini CLI | `gemini` | Research, analysis, multi-modal | Binary + OAuth file |
+
+### Agent Registry
+
+Agents are defined in `data/agent-registry.json` (custom agents) with built-in defaults in `server.py`.
+
+**Agent configuration schema:**
+```json
+{
+  "name": "agent_id",
+  "display_name": "Human Readable Name",
+  "description": "What this agent does",
+  "binary": "cli-binary-name",
+  "type": "cli",
+  "run_args": ["binary", "arg1", "{message}"],
+  "check_type": "binary",
+  "timeout": 60,
+  "builtin": false
+}
+```
+
+**Check types:**
+- `binary` — checks if binary exists in PATH
+- `oauth_file` — checks if OAuth credential file exists
+- `http` — HTTP health check against `health_url`
+- `custom` — runs `check_command`, online if exit code 0
+
+**Agent types:**
+- `cli` — executes via subprocess with `{message}` substitution
+- `http` — POSTs to `api_url` with `{"message": "..."}`
+- `mcp` — Model Context Protocol (stub, not yet implemented)
+
+### Adding Custom Agents
+
+Via the dashboard: **Agent Health** → **+ Add Agent**
+
+Or via API:
+```bash
+curl -X POST http://127.0.0.1:8081/api/agents/register \
+  -H "Content-Type: application/json" \
+  -d '{
+    "name": "my-llm",
+    "display_name": "My Local LLM",
+    "description": "Local LLM via Ollama",
+    "binary": "ollama",
+    "type": "cli",
+    "run_args": ["ollama", "run", "llama3", "{message}"],
+    "check_type": "binary",
+    "timeout": 120,
+    "router_keywords": ["local", "llama", "ollama"]
+  }'
+```
+
+### Removing Custom Agents
+
+Via the dashboard: **Agent Health** → click **Remove** on any custom agent.
+
+Or via API:
+```bash
+curl -X DELETE http://127.0.0.1:8081/api/agents/my-llm
+```
+
+Built-in agents cannot be removed.
+
+---
+
+## API Reference
+
+
+### Agents
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/agents` | `list_agents` |
+| GET | `/api/agents/health` | `get_agent_health` |
+| POST | `/api/agents/health/refresh` | `refresh_agent_health` |
+| POST | `/api/agents/register` | `register_agent` |
+| DELETE | `/api/agents/{agent_name}` | `unregister_agent` |
+| GET | `/api/agents/{name}/stats` | `get_agent_stats` |
+
+### Analytics
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/analytics/skills` | `get_skill_analytics` |
+| GET | `/api/analytics/trends` | `get_trend_analytics` |
+
+### Audit
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/audit` | `get_audit` |
+
+### Backup
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| POST | `/api/backup` | `create_backup` |
+| POST | `/api/backup/restore` | `restore_backup` |
+
+### Backups
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/backups` | `list_backups` |
+
+### Brain
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/brain` | `list_brain` |
+| GET | `/api/brain/{file_name}` | `get_brain_file` |
+| PUT | `/api/brain/{file_name}` | `update_brain_file` |
+
+### Chat
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| POST | `/api/chat` | `chat` |
+| GET | `/api/chat/history` | `get_chat_history` |
+
+### Cost
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/cost` | `get_cost` |
+| POST | `/api/cost/record` | `record_cost` |
+
+### Goals
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/goals` | `list_goals` |
+| POST | `/api/goals` | `create_goal` |
+| PUT | `/api/goals/{goal_id}` | `update_goal` |
+| DELETE | `/api/goals/{goal_id}` | `delete_goal` |
+
+### Integrations
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/integrations` | `list_integrations` |
+| POST | `/api/integrations` | `add_integration` |
+
+### Journal
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/journal/entries` | `list_journal_entries` |
+| GET | `/api/journal/entries/{entry_date}` | `get_journal_entry` |
+| PUT | `/api/journal/entries/{entry_date}` | `save_journal_entry` |
+| GET | `/api/journal/search` | `search_journal` |
+
+### Kanban
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/kanban/board` | `kanban_board` |
+| POST | `/api/kanban/dispatch` | `kanban_dispatch` |
+| POST | `/api/kanban/links` | `kanban_add_link` |
+| DELETE | `/api/kanban/links` | `kanban_remove_link` |
+| POST | `/api/kanban/tasks` | `kanban_create_task` |
+| GET | `/api/kanban/tasks/{task_id}` | `kanban_get_task` |
+| PATCH | `/api/kanban/tasks/{task_id}` | `kanban_update_task` |
+| POST | `/api/kanban/tasks/{task_id}/block` | `kanban_block_task` |
+| POST | `/api/kanban/tasks/{task_id}/comments` | `kanban_add_comment` |
+| POST | `/api/kanban/tasks/{task_id}/complete` | `kanban_complete_task` |
+| POST | `/api/kanban/tasks/{task_id}/decompose` | `kanban_decompose_task` |
+| POST | `/api/kanban/tasks/{task_id}/specify` | `kanban_specify_task` |
+| POST | `/api/kanban/tasks/{task_id}/unblock` | `kanban_unblock_task` |
+
+### Plugins
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/plugins` | `list_plugins` |
+| POST | `/api/plugins/install` | `install_plugin` |
+| DELETE | `/api/plugins/{plugin_name}` | `uninstall_plugin` |
+
+### Prompts
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/prompts` | `list_prompts` |
+
+### Root
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/` | `index` |
+| GET | `/favicon.ico` | `favicon` |
+| GET | `/favicon.svg` | `favicon_svg` |
+| GET | `/test` | `test_page` |
+
+### Router
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| POST | `/api/router/route` | `router_route` |
+| POST | `/api/router/suggest` | `router_suggest` |
+
+### Scheduler
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/scheduler/jobs` | `list_jobs` |
+| POST | `/api/scheduler/jobs` | `create_job` |
+| DELETE | `/api/scheduler/jobs/{job_id}` | `delete_job` |
+
+### Sessions
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/sessions/list` | `list_sessions` |
+| GET | `/api/sessions/{session_id}/replay` | `get_session_replay` |
+
+### Settings
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/settings` | `get_settings` |
+| PUT | `/api/settings` | `update_settings` |
+
+### Skills
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/skills` | `list_skills` |
+| GET | `/api/skills/{name}` | `get_skill` |
+| GET | `/api/skills/{name}/eval` | `get_skill_eval` |
+| POST | `/api/skills/{name}/run` | `run_skill` |
+
+### Standards
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/standards` | `list_standards` |
+| POST | `/api/standards/discover` | `discover_standards` |
+
+### Status
+
+| Method | Endpoint | Handler |
+|--------|----------|---------|
+| GET | `/api/status` | `get_status` |
+
+## Skills
+
+Skills are stored in `skills/<name>/` directories with this structure:
+
+```
+skills/
+  skill-name/
+    SKILL.md          # Instructions (YAML frontmatter + markdown)
+    learnings.md      # Accumulated run logs
+    eval.json         # Evaluation criteria
+    score-history.json # Historical scores
+    context/          # Ephemeral task inputs
+```
+
+**Skill frontmatter (SKILL.md):**
+```yaml
+---
+name: skill-name
+description: What this skill does
+version: 1.0.0
+author: Agentic OS
+tags: [category]
+---
+```
+
+**Built-in skills (17):**
+- `brainstorming` — Socratic design refinement
+- `code-review` — Automated code review
+- `content-draft` — Blog/newsletter writing
+- `cost-analytics` — Token usage tracking
+- `daily-standup` — Morning briefing
+- `devops-audit` — GCP/K8s infrastructure audit
+- `goal-planner` — Step-by-step goal planning
+- `heartbeat` — System health monitoring
+- `meeting-minutes` — Meeting notes processor
+- `memory-consolidation` — Weekly memory synthesis
+- `project-planner` — Implementation plans
+- `research-synthesis` — Web research via Gemini
+- `systematic-debug` — 4-phase root cause debugging
+- `tdd-cycle` — Red-Green-Refactor TDD
+- `backup-skill` — Backup snapshot creation
+- `test-plugin` — Plugin test fixture
+- `notion-knowledge-capture` — Third-party (via npx skills add)
+
+**Skill execution flow:**
+1. `POST /api/skills/:name/run` with optional `input` and `agent` override
+2. Router determines agent (auto-detect from keywords or SKILL.md `Primary:` line)
+3. Prompt built from SKILL.md + learnings.md + user input
+4. Agent executes via CLI
+5. Output appended to learnings.md, audit log updated
+
+---
+
+## Scheduler
+
+Two scheduling systems exist:
+
+### 1. Hermes Cron (active)
+- Managed via `hermes cron` CLI or Hermes cronjob tool
+- Currently running: `brain-guardian-autoupdate` (every 2h)
+- Persistent across restarts
+
+### 2. APScheduler (configured, not auto-started)
+- Script: `scheduler/scheduler.py`
+- Jobs stored in: `scheduler/jobs/*.json`
+- Loaded at script start, runs in background thread
+- Jobs: heartbeat (5min), daily-standup (weekdays 9am), devops-audit, memory-consolidation
+
+**Job JSON format:**
+```json
+{
+  "id": "unique-id",
+  "name": "Job Name",
+  "skill": "skill-to-run",
+  "cron": "*/5 * * * *",
+  "enabled": true
+}
+```
+
+---
+
+## Configuration
+
+### Server Configuration
+
+**`data/settings.json`:**
+```json
+{
+  "agent_preferences": {
+    "opencode": {"enabled": false, "binary": "opencode"},
+    "hermes": {"enabled": false, "binary": "hermes"},
+    "gemini": {"enabled": true, "binary": "gemini"}
+  },
+  "dashboard": {"port": 8080, "host": "127.0.0.1", "dark_mode": true},
+  "free_tier_limits": {
+    "gemini_flash": {"requests_per_day": 1500, "tokens_per_day": 1000000},
+    "openrouter_free": {"requests_per_day": 100, "tokens_per_day": 200000}
+  }
+}
+```
+
+### Hermes Model Configuration
+
+**`~/.hermes/config.yaml`:**
+```yaml
+model:
+  default: qwen/qwen3-next-80b-a3b-instruct:free
+  provider: openrouter
+  base_url: https://openrouter.ai/api/v1
+fallback_providers:
+  - provider: openrouter
+    model: openai/gpt-oss-120b:free
+  - provider: openrouter
+    model: google/gemma-4-31b-it:free
+  - provider: openrouter
+    model: nvidia/nemotron-3-super-120b-a12b:free
+```
+
+**Free model fallback chain:**
+1. `qwen/qwen3-next-80b-a3b-instruct:free` — primary (Qwen 3, 80B)
+2. `openai/gpt-oss-120b:free` — OpenAI open source
+3. `google/gemma-4-31b-it:free` — Google Gemma
+4. `nvidia/nemotron-3-super-120b-a12b:free` — NVIDIA Nemotron
+
+### Environment Variables
+
+**`~/.hermes/.env`:**
+- `OPENROUTER_API_KEY` — OpenRouter API key (required for free models)
+- `GOOGLE_API_KEY` — Google AI Studio key (optional)
+- `DEEPSEEK_API_KEY` — DeepSeek API key (optional)
+
+### Data Directory Structure
+
+```
+agentic-os/
+├── brain/                  # Persistent memory
+│   ├── memory.md           # Cross-session memory
+│   ├── business-brain.md   # Project context
+│   ├── active-projects.md  # Auto-synced from goals
+│   ├── identity.md         # Agent persona
+│   ├── constitution.md     # Governance rules
+│   ├── recent-decisions.md # Decision log
+│   └── journal/            # Daily entries (YYYY-MM-DD.md)
+├── data/
+│   ├── settings.json       # System settings
+│   ├── goals.json          # Project goals
+│   ├── chat-history.json   # Chat messages (last 200)
+│   ├── cost-history.json   # Token cost tracking
+│   ├── kanban/             # Task files (UUID.json)
+│   ├── agent-registry.json # Custom agent definitions
+│   ├── router-keywords.json # Custom agent routing keywords
+│   └── integrations.json   # Connected external apps
+├── skills/                 # Skill definitions
+├── agents/                 # Agent profiles
+│   ├── opencode/AGENTS.md
+│   ├── hermes/SOUL.md, MEMORY.md, USER.md
+│   └── gemini/GEMINI.md
+├── scheduler/jobs/         # Cron job definitions
+├── registry/plugins.json   # Plugin registry
+├── standards/              # Project standards
+├── prompts/                # Reusable prompt templates
+├── audit/audit.log         # Append-only audit trail
+└── backups/                # tar.gz snapshots
+```
+
+---
+
+## Development Guide
+
+### Adding a Dashboard Page
+
+1. Create `dashboard/pages/mypage.js` with `async function renderMypage() { ... }`
+2. Add navigation link in `dashboard/index.html`: `<a href="#mypage" class="nav-item" data-page="mypage">`
+3. Add title in `dashboard/utils.js` `PAGE_TITLES` object
+4. Add any CSS to `dashboard/styles.css`
+
+### Adding an API Endpoint
+
+1. Add route in `server.py` under the appropriate section
+2. Add Pydantic model if needed (in Models section)
+3. Add frontend API method in `dashboard/api.js`
+4. Call from page renderer
+
+### Adding a Skill
+
+```bash
+cp -r skills/_template skills/my-skill
+# Edit SKILL.md with instructions
+# Add to registry/plugins.json if desired
+```
+
+### Adding an Agent (Programmatic)
+
+```python
+# In server.py, add to BUILTIN_AGENTS dict, or use the API:
+curl -X POST http://127.0.0.1:8081/api/agents/register \
+  -H "Content-Type: application/json" \
+  -d '{"name":"my-agent","binary":"my-binary","type":"cli"}'
+```
+
+### Key Files
+
+| File | Purpose |
+|------|---------|
+| `server.py` | FastAPI backend (1780+ lines, 58+ endpoints) |
+| `dashboard/index.html` | SPA shell with sidebar nav |
+| `dashboard/app.js` | Page router and agent status polling |
+| `dashboard/api.js` | API client wrapper |
+| `dashboard/utils.js` | Shared utilities (toasts, formatting, PAGE_TITLES) |
+| `dashboard/styles.css` | All styling (dark/light theme) |
+| `dashboard/pages/*.js` | Individual page renderers |
+| `start.sh` | Start/stop/status script |
+| `data/agent-registry.json` | Custom agent persistence |
+| `brain/` | All persistent memory |
+
+### Server Lifecycle
+
+```bash
+./start.sh          # Start (port 8081 + terminal on 8082)
+./start.sh --open   # Start + open browser
+./start.sh --stop   # Stop
+./start.sh --status # Check if running
+```
+
+Logs: `tail -f /tmp/agentic-os.log`
+
+PID file: `.agentic-os.pid`
+
+---
+
+## Changelog
+
+### v1.3.0 (2026-06-28)
+- **Web Terminal**: Added browser-based bash shell (xterm.js + WebSocket PTY on port 8082)
+- **Agent Registry**: Dynamic agent registration system (add/remove custom agents via dashboard)
+- **Agent Health Page**: Complete rewrite with card view, registry table, add agent form
+- **Hermes Free Models**: Switched to Qwen 3 80B free + 3 fallback chain (OpenAI, Google, NVIDIA)
+- **Dynamic Agent Discovery**: All endpoints now use registry instead of hardcoded agent list
+- **Router Extensibility**: Custom agents can register keywords for smart routing
+- **API**: New `/api/agents`, `/api/agents/register`, `/api/agents/:name` (DELETE)
+
+### v1.2.0 (2026-06-26)
+- Agent profiles for opencode, hermes, gemini
+- APScheduler integration (scheduler.py)
+- Plugin install from git repo or template
+
+### v1.1.0 (2026-06-05)
+- Kanban board (13 endpoints)
+- Goals with auto-sync to brain
+- Journal with search
+- Agent health monitoring
+- Smart router with keyword scoring
+- Learning analytics
+- Session replay
+
+### v1.0.0 (2026-05-17)
+- Initial release: FastAPI backend, SPA dashboard, 3 agents, 16 skills

registry/plugins.json

@@ -129,4 +129,4 @@
       "type": "built-in"
     }
   ]
-}
+}

scheduler/jobs/test-audit-job.json

@@ -0,0 +1,10 @@
+{
+  "id": "c334edd1",
+  "name": "test-audit-job",
+  "skill": "daily-standup",
+  "cron": "0 9 * * *",
+  "enabled": false,
+  "created": "2026-06-28T21:39:14.908697+00:00",
+  "last_run": null,
+  "next_run": null
+}

scheduler/scheduler.py

@@ -1,8 +1,20 @@
 #!/usr/bin/env python3
-"""Agentic OS — APScheduler engine for recurring tasks"""
+"""Agentic OS — APScheduler engine for recurring tasks.
+
+Loads job definitions from scheduler/jobs/*.json and, when each cron
+trigger fires, actually executes the referenced skill by calling the
+running Agentic OS server's /api/skills/{name}/run endpoint. Running
+skills through the API means they go through the same code path as the
+dashboard: real agent invocation, real agent-health stats, and real
+eval-score population.
+
+If the server isn't reachable, the job is logged (audit) but skipped,
+so the scheduler never crashes the loop.
+"""
 import json
 import subprocess
 import sys
+import time
 from pathlib import Path
 from datetime import datetime, timezone
 
@@ -13,49 +25,119 @@ except ImportError:
     print("Install APScheduler: pip install apscheduler")
     sys.exit(1)
 
+import urllib.request
+import urllib.error
+
 BASE_DIR = Path(__file__).parent.resolve()
 JOBS_DIR = BASE_DIR / "jobs"
+# Server URL — same host, main API port. Override with AGENTIC_OS_URL env.
+SERVER_URL = "http://127.0.0.1:8080"
+RUN_TIMEOUT = 300  # seconds per skill run
 
-def run_skill(skill_name: str):
+
-    """Execute a skill by invoking the appropriate agent."""
+def log_audit(entry: dict):
     audit_file = BASE_DIR.parent / "audit" / "audit.log"
-    entry = {
+    audit_file.parent.mkdir(parents=True, exist_ok=True)
-        "action": "scheduler_run",
+    entry["timestamp"] = datetime.now(timezone.utc).isoformat()
-        "skill": skill_name,
-        "timestamp": datetime.now(timezone.utc).isoformat(),
-    }
     with open(audit_file, "a") as f:
         f.write(json.dumps(entry) + "\n")
-    print(f"[{datetime.now().isoformat()}] Ran skill: {skill_name}")
+
+
+def run_skill_via_api(skill_name: str, agent: str = "auto") -> dict:
+    """Invoke a skill through the live server API.
+
+    Returns a dict with at least {'ok': bool, 'reason'/'output': ...}.
+    """
+    url = f"{SERVER_URL}/api/skills/{skill_name}/run"
+    payload = json.dumps({"input": "", "agent": agent}).encode()
+    req = urllib.request.Request(
+        url, data=payload, headers={"Content-Type": "application/json"}, method="POST"
+    )
+    try:
+        with urllib.request.urlopen(req, timeout=RUN_TIMEOUT) as resp:
+            data = json.loads(resp.read())
+            return {"ok": True, "data": data}
+    except urllib.error.HTTPError as e:
+        return {"ok": False, "reason": f"HTTP {e.code}: {e.reason}"}
+    except urllib.error.URLError as e:
+        return {"ok": False, "reason": f"server unreachable: {e.reason}"}
+    except Exception as e:  # timeout, json error, etc.
+        return {"ok": False, "reason": str(e)}
+
+
+def run_job(job: dict):
+    skill = job.get("skill")
+    name = job.get("name", skill)
+    agent = job.get("agent", "auto")
+    print(f"[{datetime.now().isoformat()}] Firing job '{name}' -> skill '{skill}'")
+    log_audit({"action": "scheduler_run", "job": name, "skill": skill, "stage": "start"})
+
+    if not skill:
+        log_audit({"action": "scheduler_run", "job": name, "error": "no skill defined"})
+        return
+
+    result = run_skill_via_api(skill, agent)
+    if result["ok"]:
+        data = result["data"]
+        log_audit({
+            "action": "scheduler_run",
+            "job": name,
+            "skill": skill,
+            "agent": data.get("agent"),
+            "run_id": data.get("run_id"),
+            "stage": "done",
+        })
+        print(f"  -> OK (agent={data.get('agent')}, run_id={data.get('run_id')})")
+    else:
+        reason = result["reason"]
+        log_audit({"action": "scheduler_run", "job": name, "skill": skill, "error": reason})
+        print(f"  -> FAILED: {reason}")
+
 
 def load_jobs(scheduler: BackgroundScheduler):
-    """Load job definitions from jobs/ directory."""
+    if not JOBS_DIR.exists():
-    for job_file in JOBS_DIR.glob("*.json"):
+        print(f"No jobs directory at {JOBS_DIR}")
-        data = json.loads(job_file.read_text())
+        return
+    for job_file in sorted(JOBS_DIR.glob("*.json")):
+        try:
+            data = json.loads(job_file.read_text())
+        except (json.JSONDecodeError, KeyError) as e:
+            print(f"  Skipping malformed job file {job_file.name}: {e}")
+            continue
         if not data.get("enabled", True):
+            print(f"  Skipping disabled job: {data.get('name', job_file.stem)}")
+            continue
+        cron = data.get("cron")
+        skill = data.get("skill")
+        if not cron or not skill:
+            print(f"  Skipping job {data.get('name')}: missing cron or skill")
             continue
         scheduler.add_job(
-            run_skill,
+            run_job,
-            CronTrigger.from_crontab(data["cron"]),
+            CronTrigger.from_crontab(cron),
-            args=[data["skill"]],
+            args=[data],
             id=data.get("id", data["name"]),
-            name=data["name"],
+            name=data.get("name", skill),
             replace_existing=True,
+            max_instances=1,
+            coalesce=True,
         )
-        print(f"  Scheduled: {data['name']} ({data['cron']})")
+        print(f"  Scheduled: {data.get('name')} (skill={skill}, cron={cron})")
+
 
 def main():
     scheduler = BackgroundScheduler()
     load_jobs(scheduler)
     scheduler.start()
     print(f"Agentic OS Scheduler running. Jobs loaded from: {JOBS_DIR}")
+    print("Server API target: " + SERVER_URL)
     try:
         while True:
-            import time
             time.sleep(60)
     except KeyboardInterrupt:
         scheduler.shutdown()
         print("Scheduler stopped.")
 
+
 if __name__ == "__main__":
     main()

scripts/analyze_agent_time.py

@@ -0,0 +1,229 @@
+#!/usr/bin/env python3
+"""
+Agentic-OS :: Agent Time Analyzer
+-----------------------------------
+Derives total time AI agents spent on the project from event logs.
+
+The agentic-os project does NOT store explicit per-session durations,
+so we estimate total agent time with a session-gap model:
+
+  * Every logged event (audit.log line, chat message, cost entry) is a
+    timestamped touch by an agent.
+  * A "session" for an agent = a maximal run of touches where each touch
+    is within GAP seconds of the previous one.
+  * Session duration = (last touch - first touch) + TAIL.
+    TAIL accounts for the agent working after its last logged event
+    (e.g. finishing a task, writing files, thinking).
+
+This is an ESTIMATE, clearly labeled as such in the dashboard.
+
+Tunable: GAP (default 30 min), TAIL (default 2 min).
+"""
+import json
+import os
+import sys
+from datetime import datetime, timezone
+
+ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+AUDIT_LOG = os.path.join(ROOT, "audit", "audit.log")
+CHAT_HISTORY = os.path.join(ROOT, "data", "chat-history.json")
+COST_HISTORY = os.path.join(ROOT, "data", "cost-history.json")
+OUT = os.path.join(ROOT, "data", "agent-time.json")
+
+GAP_SECONDS = int(os.environ.get("AGENT_TIME_GAP", "1800"))      # 30 min
+TAIL_SECONDS = int(os.environ.get("AGENT_TIME_TAIL", "120"))    # 2 min
+
+
+def parse_ts(s):
+    if not s:
+        return None
+    try:
+        # normalize Z -> +00:00
+        s = s.replace("Z", "+00:00")
+        dt = datetime.fromisoformat(s)
+        if dt.tzinfo is None:
+            dt = dt.replace(tzinfo=timezone.utc)
+        return dt.astimezone(timezone.utc)
+    except Exception:
+        return None
+
+
+def load_audit_events():
+    """Read audit.log (JSON lines). Returns list of (ts, agent)."""
+    events = []
+    if not os.path.exists(AUDIT_LOG):
+        return events
+    with open(AUDIT_LOG, "r", encoding="utf-8") as f:
+        for line in f:
+            line = line.strip()
+            if not line:
+                continue
+            try:
+                rec = json.loads(line)
+            except Exception:
+                continue
+            ts = parse_ts(rec.get("timestamp"))
+            if ts is None:
+                continue
+            agent = rec.get("agent") or "system"
+            events.append((ts, agent))
+    return events
+
+
+def load_json_file(path):
+    if not os.path.exists(path):
+        return None
+    try:
+        with open(path, "r", encoding="utf-8") as f:
+            return json.load(f)
+    except Exception:
+        return None
+
+
+def load_chat_events():
+    events = []
+    data = load_json_file(CHAT_HISTORY)
+    if not data:
+        return events
+    for m in data.get("messages", []):
+        ts = parse_ts(m.get("timestamp"))
+        if ts is None:
+            continue
+        agent = m.get("agent") or "unknown"
+        events.append((ts, agent))
+    return events
+
+
+def load_cost_events():
+    events = []
+    data = load_json_file(COST_HISTORY)
+    if not data:
+        return events
+    for e in data.get("entries", []):
+        ts = parse_ts(e.get("timestamp"))
+        if ts is None:
+            continue
+        agent = e.get("agent") or "unknown"
+        events.append((ts, agent))
+    return events
+
+
+def compute_sessions(events):
+    """Group (ts, agent) events into per-agent sessions via gap model."""
+    by_agent = {}
+    for ts, agent in events:
+        by_agent.setdefault(agent, []).append(ts)
+
+    per_agent = {}
+    for agent, times in by_agent.items():
+        times.sort()
+        sessions = []
+        cur_start = times[0]
+        cur_last = times[0]
+        for t in times[1:]:
+            if (t - cur_last).total_seconds() <= GAP_SECONDS:
+                cur_last = t
+            else:
+                sessions.append((cur_start, cur_last))
+                cur_start = t
+                cur_last = t
+        sessions.append((cur_start, cur_last))
+        total = sum(((last - start).total_seconds() + TAIL_SECONDS) for start, last in sessions)
+        per_agent[agent] = {
+            "sessions": len(sessions),
+            "touches": len(times),
+            "total_seconds": int(total),
+            "first_seen": times[0].isoformat(),
+            "last_seen": times[-1].isoformat(),
+        }
+    return per_agent
+
+
+def fmt_hms(seconds):
+    seconds = int(seconds)
+    h = seconds // 3600
+    m = (seconds % 3600) // 60
+    s = seconds % 60
+    return f"{h}h {m}m {s}s"
+
+
+def main():
+    events = []
+    events += load_audit_events()
+    events += load_chat_events()
+    events += load_cost_events()
+
+    if not events:
+        print("No events found.", file=sys.stderr)
+        out = {
+            "project": "agentic-os",
+            "generated_at": datetime.now(timezone.utc).isoformat(),
+            "method": "session-gap estimate",
+            "gap_seconds": GAP_SECONDS,
+            "tail_seconds": TAIL_SECONDS,
+            "total_seconds": 0,
+            "total_human": "0h 0m 0s",
+            "agents": {},
+            "event_count": 0,
+            "first_seen": None,
+            "last_seen": None,
+        }
+        with open(OUT, "w", encoding="utf-8") as f:
+            json.dump(out, f, indent=2)
+        print(json.dumps(out, indent=2))
+        return
+
+    events.sort(key=lambda x: x[0])
+    per_agent = compute_sessions(events)
+    total = sum(a["total_seconds"] for a in per_agent.values())
+
+    # graphify metadata (best-effort)
+    graph_meta = {}
+    gpath = os.path.join(ROOT, "graphify-out", "graph.json")
+    if os.path.exists(gpath):
+        try:
+            with open(gpath, "r", encoding="utf-8") as f:
+                gj = json.load(f)
+            nodes = gj.get("nodes", [])
+            edges = gj.get("links", []) or gj.get("edges", [])
+            graph_meta = {
+                "nodes": len(nodes) if hasattr(nodes, "__len__") else "?",
+                "edges": len(edges) if hasattr(edges, "__len__") else "?",
+            }
+            # count communities
+            comms = set()
+            for n in nodes:
+                c = n.get("community")
+                if c is not None:
+                    comms.add(c)
+            graph_meta["communities"] = len(comms)
+            graph_meta["file"] = "graphify-out/graph.json"
+        except Exception:
+            pass
+
+    out = {
+        "project": "agentic-os",
+        "generated_at": datetime.now(timezone.utc).isoformat(),
+        "method": "session-gap estimate (GAP=%ds, TAIL=%ds)" % (GAP_SECONDS, TAIL_SECONDS),
+        "graph": graph_meta,
+        "gap_seconds": GAP_SECONDS,
+        "tail_seconds": TAIL_SECONDS,
+        "total_seconds": total,
+        "total_human": fmt_hms(total),
+        "agents": per_agent,
+        "event_count": len(events),
+        "first_seen": events[0][0].isoformat(),
+        "last_seen": events[-1][0].isoformat(),
+    }
+
+    os.makedirs(os.path.dirname(OUT), exist_ok=True)
+    with open(OUT, "w", encoding="utf-8") as f:
+        json.dump(out, f, indent=2)
+    print("Wrote", OUT)
+    print("TOTAL:", out["total_human"], "across", len(per_agent), "agents,", len(events), "events")
+    for agent, a in sorted(per_agent.items(), key=lambda kv: -kv[1]["total_seconds"]):
+        print(f"  {agent:12s} {fmt_hms(a['total_seconds']):>14s}  sessions={a['sessions']:<4d} touches={a['touches']}")
+
+
+if __name__ == "__main__":
+    main()

scripts/update-api-docs.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python3
+"""
+Extract API documentation from server.py and update docs/README.md
+Run this after adding/removing/changing API endpoints.
+"""
+import re
+import sys
+from pathlib import Path
+
+BASE = Path(__file__).parent.parent.resolve()  # Go up from scripts/ to project root
+SERVER = BASE / "server.py"
+DOCS = BASE / "docs" / "README.md"
+
+def extract_endpoints():
+    """Parse server.py for FastAPI route definitions."""
+    content = SERVER.read_text()
+
+    # Match @app.get/post/put/patch/delete("path")
+    pattern = r'@app\.(get|post|put|patch|delete)\("([^"]+)"'
+    endpoints = []
+    for match in re.finditer(pattern, content):
+        method = match.group(1).upper()
+        path = match.group(2)
+        # Find the function name after the decorator
+        rest = content[match.end():match.end()+200]
+        func_match = re.search(r'def\s+(\w+)', rest)
+        func_name = func_match.group(1) if func_match else "?"
+        endpoints.append((method, path, func_name))
+
+    return endpoints
+
+def generate_api_table(endpoints):
+    """Generate markdown table for API reference."""
+    # Group by category (based on path prefix)
+    categories = {}
+    for method, path, func in endpoints:
+        # Extract category from path
+        parts = path.split('/')
+        if len(parts) >= 3:
+            cat = parts[2]  # e.g. "status", "brain", "skills"
+        else:
+            cat = "root"
+        categories.setdefault(cat, []).append((method, path, func))
+
+    lines = []
+    for cat in sorted(categories.keys()):
+        lines.append(f"\n### {cat.replace('-', ' ').title()}\n")
+        lines.append("| Method | Endpoint | Handler |")
+        lines.append("|--------|----------|---------|")
+        for method, path, func in sorted(categories[cat], key=lambda x: x[1]):
+            lines.append(f"| {method} | `{path}` | `{func}` |")
+
+    return "\n".join(lines)
+
+def update_docs():
+    """Update the API reference section in docs/README.md."""
+    endpoints = extract_endpoints()
+    new_api_section = generate_api_table(endpoints)
+
+    if not DOCS.exists():
+        print(f"ERROR: {DOCS} not found")
+        sys.exit(1)
+
+    content = DOCS.read_text()
+
+    # Find and replace the API Reference section
+    # Look for "## API Reference" until next "##" section
+    pattern = r'(## API Reference\n).*?(?=\n## )'
+    replacement = f"## API Reference\n\n{new_api_section}\n"
+
+    if re.search(pattern, content, re.DOTALL):
+        new_content = re.sub(pattern, replacement, content, flags=re.DOTALL)
+        DOCS.write_text(new_content)
+        print(f"Updated {DOCS} with {len(endpoints)} API endpoints")
+    else:
+        print("WARNING: Could not find '## API Reference' section in docs")
+        print("Adding it before the last section...")
+        # Find last ## section
+        last_section = content.rfind("\n## ")
+        if last_section >= 0:
+            new_content = content[:last_section] + f"\n{replacement}\n" + content[last_section:]
+            DOCS.write_text(new_content)
+            print(f"Updated {DOCS} with {len(endpoints)} API endpoints")
+        else:
+            print("ERROR: No sections found in docs")
+            sys.exit(1)
+
+if __name__ == "__main__":
+    update_docs()

skills-lock.json

@@ -0,0 +1,77 @@
+{
+  "version": 1,
+  "skills": {
+    "firebase-ai-logic-basics": {
+      "source": "firebase/skills",
+      "sourceType": "github",
+      "skillPath": "skills/firebase-ai-logic-basics/SKILL.md",
+      "computedHash": "aba2d689236a21ac7989286b88ecb3399d616b90f2dd8946e675466e57802c35"
+    },
+    "firebase-app-hosting-basics": {
+      "source": "firebase/skills",
+      "sourceType": "github",
+      "skillPath": "skills/firebase-app-hosting-basics/SKILL.md",
+      "computedHash": "562f27d560ff640a1e18ec4f5dd4ae70bd98447433c077be19292793ae095572"
+    },
+    "firebase-auth-basics": {
+      "source": "firebase/skills",
+      "sourceType": "github",
+      "skillPath": "skills/firebase-auth-basics/SKILL.md",
+      "computedHash": "f4850f578bacdda96cacaa57b5e1121ec047e99bf7d389033042b1975af91040"
+    },
+    "firebase-basics": {
+      "source": "firebase/skills",
+      "sourceType": "github",
+      "skillPath": "skills/firebase-basics/SKILL.md",
+      "computedHash": "8210ee53231b8299df100561d4ef776d39a293fd54403008bd738c65a856d54f"
+    },
+    "firebase-crashlytics": {
+      "source": "firebase/skills",
+      "sourceType": "github",
+      "skillPath": "skills/firebase-crashlytics/SKILL.md",
+      "computedHash": "62a51efdc3240eed27697e14bbb8a29ebb8c94530fd3a1c851e747b90804d69b"
+    },
+    "firebase-data-connect": {
+      "source": "firebase/skills",
+      "sourceType": "github",
+      "skillPath": "skills/firebase-data-connect-basics/SKILL.md",
+      "computedHash": "92d3dff5c94753c4077cd44a5c7c1f5e077b8c07dfe28455776204fe4f087d81"
+    },
+    "firebase-firestore": {
+      "source": "firebase/skills",
+      "sourceType": "github",
+      "skillPath": "skills/firebase-firestore/SKILL.md",
+      "computedHash": "be5ed12b7402b1f36364e20d4f9ccd2caac90302e23427395a02570db9f1434a"
+    },
+    "firebase-hosting-basics": {
+      "source": "firebase/skills",
+      "sourceType": "github",
+      "skillPath": "skills/firebase-hosting-basics/SKILL.md",
+      "computedHash": "fd0fede590512379a3103b74a7c1e612e38e6948b08e763a75962cd8c7f5b8e2"
+    },
+    "firebase-remote-config-basics": {
+      "source": "firebase/skills",
+      "sourceType": "github",
+      "skillPath": "skills/firebase-remote-config-basics/SKILL.md",
+      "computedHash": "d5e9090dec35e050be958b72b672e39bd931014ebb311bac3a46f542fc04e10d"
+    },
+    "firebase-security-rules-auditor": {
+      "source": "firebase/skills",
+      "sourceType": "github",
+      "skillPath": "skills/firebase-security-rules-auditor/SKILL.md",
+      "computedHash": "7d05c33d2e00c1d26cbd99ae174272fdd962e63b67c801e2fc050cc63e681723"
+    },
+    "notion-knowledge-capture": {
+      "source": "openai/skills",
+      "sourceType": "github",
+      "skillPath": "skills/.curated/notion-knowledge-capture/SKILL.md",
+      "computedHash": "c1376422aec0fb3a4733e5a8a99eed4feff24fa45e25a2ffddaf07a68eed9198"
+    },
+    "xcode-project-setup": {
+      "source": "firebase/skills",
+      "sourceType": "github",
+      "skillPath": "skills/xcode-project-setup/SKILL.md",
+      "computedHash": "e7ddb878c879eda7a3e462cebebcebb827d90836e4cb8a11b513e54403176e7d"
+    }
+  }
+}

skills/audit-test-plugin/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: _template
+description: Template for creating new Agentic OS skills
+version: 1.0.0
+author: Agentic OS
+tags: [template, meta]
+---
+
+# {Skill Name}
+
+## Description
+Brief description of what this skill does.
+
+## When to Use
+- Trigger condition 1
+- Trigger condition 2
+
+## Input
+- What this skill expects as input
+
+## Process
+1. Step one
+2. Step two
+3. Step three
+
+## Output
+- What this skill produces
+
+## Agent Assignment
+- Primary: opencode / hermes / gemini
+- Fallback: {fallback agent}
+
+## Dependencies
+- Any prerequisites

skills/audit-test-plugin/eval.json

@@ -0,0 +1,7 @@
+{
+  "criteria": [
+    { "name": "completeness", "weight": 0.4 },
+    { "name": "accuracy", "weight": 0.3 },
+    { "name": "clarity", "weight": 0.3 }
+  ]
+}

skills/audit-test-plugin/learnings.md

@@ -0,0 +1,6 @@
+# Learnings
+
+Add lessons learned from each run here.
+
+## Initial Setup
+- Template created with standard skill structure

skills/audit-test-plugin/score-history.json

@@ -0,0 +1 @@
+[]

skills/backup-skill/learnings.md

@@ -4,3 +4,7 @@
 - Exclude data/settings.json from backups
 - Keep last 30 backups, remove older
 - Timestamp filenames for easy sorting
+
+## 2026-06-26
+- opencode timed out on backup-skill execution
+- Recommend: use hermes agent for backup-skill

skills/brainstorming/learnings.md

@@ -3,3 +3,7 @@
 ## 2026-05-17
 - Socratic questioning reveals hidden constraints
 - 3+ alternatives before recommending
+
+## 2026-06-23
+- opencode consistently times out on brainstorming runs (4+ attempts logged)
+- Recommend: use hermes agent (not opencode) for brainstorming tasks

skills/code-review/learnings.md

@@ -2,3 +2,24 @@
 
 ## 2026-05-17
 - Follows Superpowers methodology for code review
+
+## 2026-06-28
+- opencode consistently times out on non-code tasks → route to hermes
+
+## 2026-07-25 (Run 07aca844)
+- Agent: opencode
+- Input: Review the server.py router logic
+- Output: ⏱ Agent 'opencode' timed out.
+
+OpenCode's model is taking too long. Try running `opencode run "Execute the 'code-review' skill.
+
+## Skill Instructions
+---
+"` directly in your terminal.
+
+**Message:** Execute the 'code-review' skill.
+
+## Skill Instructions
+---
+name: code-review
+description: Automated

skills/code-review/score-history.json

@@ -1 +1 @@
-[]
+[]

skills/daily-standup/learnings.md

@@ -4,99 +4,41 @@
 - Reads from brain/ files and audit log
 - Runs best at session start
 
-## 2026-05-18 (Run 7215be12)
+## 2026-05-18
+- Multipleup runs confirm: consistent pattern of reading brain/ + audit log
+- Both opencode and hermes agents execute standup successfully
+- Known backup filenagentic-os-20260517_163610.tar.gz created & restored
+
+## 2026-06-23
+- hermes agent returns partial output when session times out mid-execution
+- openerate agent reads brain/ files correctly via Read tool
+- Recommend: use `hermes chat -q "morning briefing"` for faster standup execution
+
+## 2026-07-25 (Run efcfb319)
 - Agent: hermes
-- Input: (none)
+- Input: Generate today's standup notes
-- Output: I'll execute the daily-standup skill by reading the relevant brain files and audit log.
+- Output: I'll execute the daily-standup skill. Let me gather the context from the
-Here's your morning briefing:
+brain files and audit log.
-AGENTIC OS — Daily Standup (May 18, 2026)
+Now let me check the audit log and pending tasks (kanban/goals).
-YESTERDAY (May 17):
+Let me read the kanban task files to see pending work, and check today's
-- Agentic OS project created from scratch — full 3-agent architecture (opencode + Hermes + Gemini CLI)
+journal.
-- 51 features + 10 extras planned across 8 phases
+I have all the context I need. Here's today's daily standup.
-- Dashboard built: FastAPI backend + vanilla JS SPA
+══════════════════════════════════════════════
-- Skills hub seeded with 15+ skills (DevOps, content, research, coding, productivity)
+DAILY STANDUP — Saturday, July 25, 2026
-- Git auto-versioning enabled
+══════════════════════════════════════════════
+YESTERDAY / RECENT ACTIVITY (last 24h + recent log)
+- 2026
 
-## 2026-05-18 (Run 2de16a6e)
+## 2026-07-25 (Run ba720ad7)
 - Agent: hermes
-- Input: (none)
+- Input: standup
-- Output: I'll execute the daily-standup skill by reading the relevant brain files and audit log.
+- Output: I'll execute the daily-standup skill. Let me gather context from the
-Daily Standup — Monday, May 18, 2026
+brain files, audit log, and task systems in parallel.
-Yesterday (May 17)
+Now let me check the kanban tasks, goals, and today's journal entry.
-- Built Agentic OS from scratch — full project structure, 51 features + 10 extras
+Let me read the kanban task files to assess their status.
-- Configured 3-agent architecture: opencode + Hermes + Gemini CLI
+Daily Standup gathered. Here's the briefing.
-- Set up FastAPI dashboard with SPA frontend
+══════════════════════════════════════════════
-- Created 15+ skills following _template/ convention
+DAILY STANDUP — Saturday, July 25, 2026
-- Ran heartbeat and devops-audit skills successfully
+══════════════════════════════════════════════
-- Created + restored backup snapshot (agentic-os-20260517
+YESTERDAY / RECENT ACTIVITY (last 24h + recent log)
-
+- 2026-07-25 17:10 
-## 2026-05-18 (Run 524c5285)
-- Agent: hermes
-- Input: (none)
-- Output: I'll execute the daily-standup skill by reading the relevant brain files and audit log.
-Here's your morning briefing:
-AGENTIC OS — Daily Standup (May 18, 2026)
-YESTERDAY (May 17):
-- Built Agentic OS v1.0 from scratch — full 3-agent architecture (opencode + Hermes + Gemini CLI)
-- Created 51 features + 10 extras across 7 layers
-- Set up FastAPI dashboard + SPA frontend
-- Created 15+ skills with eval scoring and learnings tracking
-- Ran heartbeat and devops-audit skills successfully
-- Tested backup
-
-## 2026-05-18 (Run dacf584a)
-- Agent: hermes
-- Input: (none)
-- Output: I'll execute the daily-standup skill by reading the relevant brain files and audit log.
-Now let me check the last 24h of audit entries more carefully and get the latest entries:
-Here's your morning briefing:
-AGENTIC OS — Daily Standup (May 18, 2026)
-YESTERDAY (May 17):
-- Agentic OS project created from scratch — full 3-agent architecture (opencode + Hermes + Gemini CLI)
-- 51 features + 10 extras planned across 8 phases
-- Dashboard built: FastAPI backend + vanilla JS SPA
-- Skills hub seeded with 
-
-## 2026-05-18 (Run b6069709)
-- Agent: opencode
-- Input: (none)
-- Output: # Agentic OS — Daily Standup (May 18, 2026)
-
-## Yesterday (May 17)
-- Built Agentic OS v1.0 from scratch — full 3-agent architecture, 7 layers, 51 features + 10 extras
-- FastAPI dashboard + SPA frontend created with 13 dashboard pages
-- 15+ skills seeded (_template/, heartbeat, devops-audit, content-draft, code-review, daily-standup, etc.)
-- All 3 agents tested: opencode, Hermes, Gemini CLI
-- Backup created & restored successfully (agentic-os-20260517_163610.tar.gz)
-- Standards discovery run comp
-
-## 2026-05-18 (Run a6d21650)
-- Agent: hermes
-- Input: (none)
-- Output: Let me gather the data for today's standup.
-AGENTIC OS — Daily Standup (May 18, 2026)
-YESTERDAY (May 17):
-- Built Agentic OS v1.0 from scratch — full 3-agent architecture (opencode + Hermes + Gemini CLI)
-- 51 features + 10 extras across 7 layers
-- FastAPI dashboard + SPA frontend live
-- 15+ skills created with eval scoring and learnings tracking
-- Heartbeat + devops-audit skills ran successfully
-- Backup created and restored (agentic-os-20260517_163610.tar.gz)
-- Standards discovery ran
-- Tested 
-
-## 2026-05-18 (Run e1fffffb)
-- Agent: opencode
-- Input: (none)
-- Output: **Agentic OS — Daily Standup (May 18, 2026)**
-
-**Yesterday (May 17)**
-- Built Agentic OS v1.0 from scratch — 3-agent architecture, 7 layers, 51+10 features
-- FastAPI dashboard + 13 SPA pages, 15+ skills seeded
-- All 3 agents tested (opencode, Hermes, Gemini CLI)
-- Backup created & restored, standards discovery run
-
-**Overnight Activity**
-- Multiple daily-standup skill runs across opencode + Hermes (runs 7215be12 through a6d21650)
-- Heartbeat tested successfully
-- Chat interactions across all 3 a

skills/daily-standup/score-history.json

@@ -1 +1 @@
-[]
+[]

skills/firebase-ai-logic-basics

@@ -0,0 +1 @@
+../.agents/skills/firebase-ai-logic-basics

skills/firebase-app-hosting-basics

@@ -0,0 +1 @@
+../.agents/skills/firebase-app-hosting-basics

skills/firebase-auth-basics

@@ -0,0 +1 @@
+../.agents/skills/firebase-auth-basics

skills/firebase-basics

@@ -0,0 +1 @@
+../.agents/skills/firebase-basics

skills/firebase-crashlytics

@@ -0,0 +1 @@
+../.agents/skills/firebase-crashlytics

skills/firebase-data-connect

@@ -0,0 +1 @@
+../.agents/skills/firebase-data-connect

skills/firebase-firestore

@@ -0,0 +1 @@
+../.agents/skills/firebase-firestore

skills/firebase-hosting-basics

@@ -0,0 +1 @@
+../.agents/skills/firebase-hosting-basics

skills/firebase-remote-config-basics

@@ -0,0 +1 @@
+../.agents/skills/firebase-remote-config-basics

skills/firebase-security-rules-auditor

@@ -0,0 +1 @@
+../.agents/skills/firebase-security-rules-auditor

skills/goal-planner/learnings.md

@@ -4,3 +4,6 @@
 - Always clarify goal with targeted questions first
 - Identify critical path for complex projects
 - Break into milestones, then tasks, then estimates
+
+## 2026-06-28
+- opencode consistently times out on non-code tasks → route to hermes

skills/memory-consolidation/learnings.md

@@ -4,3 +4,53 @@
 - Run weekly to keep memory files under 600 words
 - Archive decisions older than 30 days
 - Check for contradictions across skills
+
+## 2026-06-26
+- hermes timed out on memory-consolidation (model too slow)
+- Recommend: try shorter queries or check OpenRouter rate limits
+
+## 2026-06-28
+- All 18 learnings.md files under 600 words — no compression needed
+- All score-history.json files empty — no pruning needed
+- recent-decisions.md: 3 archived entries (older than 30 days), 0 recent
+- No contradictions found across skill learnings
+- Stale truncated run logs cleaned from memory-consolidation, code-review, goal-planner, test-plugin
+
+## 2026-06-29 (Run 2)
+- All 18 learnings.md files still under 600 words (largest: memory-consolidation at 186)
+- All 18 score-history.json files empty — no pruning needed
+- recent-decisions.md: 3 archived entries (from 2026-05-17), 0 recent — no archiving needed
+- No contradictions found across skill learnings
+- Cleaned stale truncated run log from memory-consolidation learnings.md (leftover from previous run)
+
+## 2026-07-17 (Run — full)
+- Agent: hermes
+- Input: (none)
+- All 18 learnings.md files under 600 words (largest: memory-consolidation at 245) — no compression needed
+- All 18 score-history.json files empty (`[]`) — no pruning needed
+- recent-decisions.md: 3 archived entries (from 2026-05-17, already >30 days old), 0 recent — no archiving needed
+- No contradictions found across skill learnings
+- Cleaned stale truncated run log (Run 0e7b20b5) from this file — it cut off mid-line and was leftover from an earlier failed run
+
+## 2026-07-17 (Run 4f8a2c19)
+- Agent: hermes
+- Input: (none)
+- 19 learnings.md files under 600 words (largest: memory-consolidation at 333) — no compression needed
+- All 19 score-history.json files empty (`[]`) — no pruning needed
+- recent-decisions.md: 3 archived entries (from 2026-05-17, >30 days old), 0 recent — no archiving needed
+- No contradictions found across skill learnings
+- Cleaned stale truncated run log (Run 82b75bcd) and stale opencode-timeout logs from firebase-hosting-basics
+
+## 2026-07-17 (Run 5e7d871e)
+- Agent: hermes
+- Input: (none)
+- Output: ⏱ Hermes timed out.
+
+The model took too long to respond. Try a shorter query or check your OpenRouter rate limits.
+
+**Message:** Execute the 'memory-consolidation' skill.
+
+## Skill Instructions
+---
+name: memory-consolidation
+desc

skills/notion-knowledge-capture

@@ -0,0 +1 @@
+../.agents/skills/notion-knowledge-capture

skills/tdd-cycle/learnings.md

@@ -5,3 +5,7 @@
 - GREEN phase: minimal code to pass
 - REFACTOR phase: clean while tests stay green
 - Never skip RED phase
+
+## 2026-06-26
+- opencode timed out 3 times on tdd-cycle execution
+- Recommend: use hermes agent for tdd-cycle skill

skills/test-plugin/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: _template
+description: Template for creating new Agentic OS skills
+version: 1.0.0
+author: Agentic OS
+tags: [template, meta]
+---
+
+# {Skill Name}
+
+## Description
+Brief description of what this skill does.
+
+## When to Use
+- Trigger condition 1
+- Trigger condition 2
+
+## Input
+- What this skill expects as input
+
+## Process
+1. Step one
+2. Step two
+3. Step three
+
+## Output
+- What this skill produces
+
+## Agent Assignment
+- Primary: opencode / hermes / gemini
+- Fallback: {fallback agent}
+
+## Dependencies
+- Any prerequisites

skills/test-plugin/eval.json

@@ -0,0 +1,7 @@
+{
+  "criteria": [
+    { "name": "completeness", "weight": 0.4 },
+    { "name": "accuracy", "weight": 0.3 },
+    { "name": "clarity", "weight": 0.3 }
+  ]
+}

skills/test-plugin/learnings.md

@@ -0,0 +1,9 @@
+# Learnings
+
+Add lessons learned from each run here.
+
+## Initial Setup
+- Template created with standard skill structure
+
+## 2026-06-28
+- opencode timed out on test-plugin execution; non-code tasks should route to hermes

skills/test-plugin/score-history.json

@@ -0,0 +1 @@
+[]

skills/xcode-project-setup

@@ -0,0 +1 @@
+../.agents/skills/xcode-project-setup

start-agentic-os.sh

@@ -0,0 +1,43 @@
+#!/usr/bin/env bash
+# Agentic OS server launcher — idempotent + fully detached.
+# Safe to run repeatedly: if the server is already listening it does nothing.
+# This is the FALLBACK path used only when systemd is unavailable
+# (e.g. a WSL instance that hasn't started the user session).
+set -u
+
+DIR="/home/austin/agentic-os"
+LOG="/tmp/agentic-os.log"
+PIDFILE="$DIR/.agentic-os.pid"
+HOST="0.0.0.0"
+PORT="8080"
+
+# Already serving? Then do nothing (idempotent).
+if ss -ltn 2>/dev/null | grep -q ":$PORT "; then
+  echo "Agentic OS already listening on :$PORT — nothing to do."
+  exit 0
+fi
+
+cd "$DIR" || { echo "FATAL: cannot cd to $DIR"; exit 1; }
+
+# Remove a stale pidfile if its process is no longer alive.
+if [ -f "$PIDFILE" ]; then
+  OLD="$(cat "$PIDFILE" 2>/dev/null)"
+  if [ -n "$OLD" ] && ! kill -0 "$OLD" 2>/dev/null; then
+    rm -f "$PIDFILE"
+  fi
+fi
+
+# setsid detaches into a new session so the server outlives the launching
+# shell (cron tick, session end, terminal close).
+setsid python3 server.py >> "$LOG" 2>&1 < /dev/null &
+echo "$!" > "$PIDFILE"
+echo "Launched Agentic OS (pid $(cat "$PIDFILE")) — log: $LOG"
+
+# Brief wait, then verify it actually came up.
+sleep 4
+if ss -ltn 2>/dev/null | grep -q ":$PORT "; then
+  echo "OK: serving on http://$HOST:$PORT"
+else
+  echo "WARN: not listening after 4s — tail of $LOG:"
+  tail -15 "$LOG"
+fi

start.sh

@@ -1,27 +1,104 @@
 #!/usr/bin/env bash
+# Agentic OS Quick Start
+# Usage: ./start.sh          — start server
+#        ./start.sh --open   — start server + open browser
+#        ./start.sh --stop   — stop running server
+#        ./start.sh --status — check if running
+
 set -euo pipefail
 
-echo "Starting Agentic OS Dashboard..."
+PORT="${PORT:-8081}"
-echo ""
+PID_FILE=".agentic-os.pid"
+DASHBOARD_URL="http://127.0.0.1:${PORT}"
 
-# Check if server.py exists
+# ── Handle flags ───────────────────────────────────────────────────────────
-if [ ! -f server.py ]; then
+
-    echo "ERROR: server.py not found. Are you in the right directory?"
+case "${1:-}" in
-    exit 1
+  --stop)
+    if [ -f "$PID_FILE" ]; then
+      PID=$(cat "$PID_FILE")
+      if kill -0 "$PID" 2>/dev/null; then
+        kill "$PID" && echo "Agentic OS stopped (PID $PID)."
+        rm -f "$PID_FILE"
+      else
+        echo "Agentic OS is not running (stale PID file removed)."
+        rm -f "$PID_FILE"
+      fi
+    else
+      echo "Agentic OS is not running."
+    fi
+    exit 0
+    ;;
+  --status)
+    if [ -f "$PID_FILE" ] && kill -0 "$(cat "$PID_FILE")" 2>/dev/null; then
+      echo "Agentic OS is running (PID $(cat "$PID_FILE")) — $DASHBOARD_URL"
+    else
+      echo "Agentic OS is not running."
+    fi
+    exit 0
+    ;;
+esac
+
+# ── Already running? ───────────────────────────────────────────────────────
+
+if [ -f "$PID_FILE" ] && kill -0 "$(cat "$PID_FILE")" 2>/dev/null; then
+  echo "Agentic OS is already running at $DASHBOARD_URL"
+  echo "Use ./start.sh --stop to stop it first."
+  exit 0
 fi
 
-# Check dependencies
+# ── Setup ──────────────────────────────────────────────────────────────────
-pip3 install -r requirements.txt --quiet 2>/dev/null
 
-# Get port from settings or default
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-PORT=8080
+cd "$SCRIPT_DIR"
-if command -v python3 &>/dev/null; then
+
-    PORT=$(python3 -c "import json; f=open('data/settings.json'); d=json.load(f); print(d.get('dashboard',{}).get('port',8080)); f.close()" 2>/dev/null || echo "8080")
+# Activate venv if it exists
+if [ -d "venv" ]; then
+  source venv/bin/activate
 fi
 
-echo "Dashboard: http://127.0.0.1:${PORT}"
+# Install deps if needed
-echo "Press Ctrl+C to stop"
+if ! python3 -c "import fastapi" 2>/dev/null; then
+  echo "Installing dependencies..."
+  pip3 install -r requirements.txt --quiet
+fi
+
+# ── Start server ───────────────────────────────────────────────────────────
+
+echo ""
+echo "  Agentic OS Dashboard"
+echo "  ─────────────────────"
+echo "  Starting on port ${PORT}..."
+echo "  URL: ${DASHBOARD_URL}"
+echo "  Press Ctrl+C to stop"
 echo ""
 
-# Start server
+nohup python3 server.py --port "$PORT" --host 0.0.0.0 > /tmp/agentic-os.log 2>&1 &
-python3 server.py --port "${PORT}"
+echo $! > "$PID_FILE"
+
+# Wait for server to be ready
+for i in $(seq 1 10); do
+  if curl -s http://127.0.0.1:${PORT}/api/status > /dev/null 2>&1; then
+    echo "  Ready! ($DASHBOARD_URL)"
+    break
+  fi
+  sleep 0.5
+done
+
+# ── Open browser ───────────────────────────────────────────────────────────
+
+case "${1:-}" in
+  --open)
+    echo "  Opening browser..."
+    if command -v xdg-open &>/dev/null; then
+      xdg-open "$DASHBOARD_URL" 2>/dev/null || true
+    elif command -v open &>/dev/null; then
+      open "$DASHBOARD_URL" 2>/dev/null || true
+    fi
+    ;;
+esac
+
+echo ""
+echo "  Logs: tail -f /tmp/agentic-os.log"
+echo "  Stop: ./start.sh --stop"
+echo ""