diff --git a/AGENTS.md b/AGENTS.md index 3e1c865..abc4488 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -192,14 +192,15 @@ Your role is to act as the **kernel** of this system: route tasks to the right a ├── backup.sh # Manual backup [E3] ├── restore.sh # Manual restore [E3] │ -├── brain/ # [F2, F7, F10, F49, F50] Shared context +├── brain/ # [F2, F7, F10, F49, F50, F54] Shared context │ ├── business-brain.md │ ├── memory.md │ ├── recent-decisions.md │ ├── active-projects.md │ ├── constraints.md │ ├── identity.md -│ └── constitution.md +│ ├── constitution.md +│ └── journal/ # [F54] Daily markdown entries (YYYY-MM-DD.md) │ ├── skills/ # [F5, F8, F15, F17] Skills Hub │ ├── _template/ @@ -272,7 +273,14 @@ Your role is to act as the **kernel** of this system: route tasks to the right a │ ├── prompts.js │ ├── standards.js │ ├── settings.js -│ └── setup-wizard.js +│ ├── setup-wizard.js +│ ├── kanban.js # [F52] Kanban Board (v0.2.0) +│ ├── goals.js # [F53] Goals (v0.2.0) +│ ├── journal.js # [F54] Journal (v0.2.0) +│ ├── agent-health.js # [F55] Agent Health (v0.2.0) +│ ├── smart-router.js # [F56] Smart Router (v0.2.0) +│ ├── learning-analytics.js # [F57] Learning Analytics (v0.2.0) +│ └── session-replay.js # [F58] Session Replay (v0.2.0) │ ├── audit/ # [F38] Audit Trail │ └── audit.log @@ -295,7 +303,9 @@ Your role is to act as the **kernel** of this system: route tasks to the right a ├── data/ # Runtime data │ ├── settings.json │ ├── cost-history.json -│ └── agent-routes.json +│ ├── agent-routes.json +│ ├── kanban/ # [F52] Kanban task JSON files +│ └── goals.json # [F53] Goals storage │ └── .git/ # [E2] Auto-versioning ``` @@ -351,8 +361,9 @@ When you (an AI agent) are dropped into this directory for the first time: --- -## API Endpoints (server.py FastAPI) +## API Endpoints (server.py FastAPI, 58 total — 28 original + 30 v0.2.0) +### Core (28 original endpoints) | Method | Endpoint | Purpose | |--------|----------|---------| | GET | `/api/status` | System health + 3 agent status | @@ -378,6 +389,64 @@ When you (an AI agent) are dropped into this directory for the first time: | GET | `/api/standards` | List standards | | POST | `/api/standards/discover` | Run standards discovery | +### Kanban Board (v0.2.0) — 13 endpoints +| Method | Endpoint | Purpose | +|--------|----------|---------| +| GET | `/api/kanban/board` | Get kanban board (all columns + tasks) | +| GET | `/api/kanban/tasks/{id}` | Get single task | +| POST | `/api/kanban/tasks` | Create task | +| PATCH | `/api/kanban/tasks/{id}` | Update task fields | +| POST | `/api/kanban/tasks/{id}/complete` | Mark task done | +| POST | `/api/kanban/tasks/{id}/block` | Block task | +| POST | `/api/kanban/tasks/{id}/unblock` | Unblock task | +| POST | `/api/kanban/tasks/{id}/comments` | Add comment | +| POST | `/api/kanban/links` | Link parent/child tasks | +| DELETE | `/api/kanban/links` | Unlink tasks | +| POST | `/api/kanban/dispatch` | Dispatch triage tasks | +| POST | `/api/kanban/tasks/{id}/specify` | Generate spec | +| POST | `/api/kanban/tasks/{id}/decompose` | Decompose into subtasks | + +### Goals (v0.2.0) — 4 endpoints +| Method | Endpoint | Purpose | +|--------|----------|---------| +| GET | `/api/goals` | List all goals | +| POST | `/api/goals` | Create goal (auto-syncs to brain/active-projects.md) | +| PUT | `/api/goals/{id}` | Update goal progress/status | +| DELETE | `/api/goals/{id}` | Delete goal | + +### Journal (v0.2.0) — 4 endpoints +| Method | Endpoint | Purpose | +|--------|----------|---------| +| GET | `/api/journal/entries` | List all entry dates | +| GET | `/api/journal/entries/{date}` | Get entry content | +| PUT | `/api/journal/entries/{date}` | Save entry (creates/updates brain/journal/YYYY-MM-DD.md) | +| GET | `/api/journal/search?q=` | Full-text search across entries | + +### Agent Health (v0.2.0) — 3 endpoints +| Method | Endpoint | Purpose | +|--------|----------|---------| +| GET | `/api/agents/health` | Get live status of all 3 agents | +| GET | `/api/agents/{name}/stats` | Get per-agent statistics | +| POST | `/api/agents/health/refresh` | Force refresh all status checks | + +### Smart Router (v0.2.0) — 2 endpoints +| Method | Endpoint | Purpose | +|--------|----------|---------| +| POST | `/api/router/suggest` | Suggest best agent for a task description | +| POST | `/api/router/route` | Route task to a specific agent | + +### Learning Analytics (v0.2.0) — 2 endpoints +| Method | Endpoint | Purpose | +|--------|----------|---------| +| GET | `/api/analytics/skills` | Skill evaluation scores across all skills | +| GET | `/api/analytics/trends` | Score history trends per skill | + +### Session Replay (v0.2.0) — 2 endpoints +| Method | Endpoint | Purpose | +|--------|----------|---------| +| GET | `/api/sessions/list` | List opencode sessions | +| GET | `/api/sessions/{id}/replay` | Get session message content | + --- ## Version History diff --git a/README.md b/README.md index 58c1936..cc209ea 100644 --- a/README.md +++ b/README.md @@ -5,6 +5,7 @@ FastAPI 3 Agents 16 Skills + v0.2.0 Status: Stable dev.to article

@@ -34,6 +35,13 @@ A locally-hosted operating system for AI agents — an open-source GitHub reposi | **🔌 Plugin Registry** | Marketplace-style plugin management (extensible via skills) | | **🎨 Dark/Light Theme** | GitHub-style dark mode + clean light theme, toggle from sidebar | | **⚡ Zero API Costs** | Built for free tiers — Gemini Flash, OpenRouter free models, local opencode | +| **📋 Kanban Board** | Visual task management — drag-and-drop columns, priority/status filtering, block/unblock, detail view | +| **🎯 Goals** | Project targets with progress tracking, auto-syncs to `brain/active-projects.md` | +| **📓 Journal** | Daily markdown entries stored as `brain/journal/YYYY-MM-DD.md` with full-text search | +| **❤️ Agent Health** | Real-time monitoring of opencode, Hermes, and Gemini CLI availability | +| **🧭 Smart Router** | Keyword-based task routing with confidence scoring — suggests best agent for any task | +| **📊 Learning Analytics** | Skill evaluation scores, performance trends, and historical charts | +| **🎬 Session Replay** | Browse and replay past opencode sessions from the dashboard | --- @@ -149,7 +157,7 @@ agentic-os/ │ ├── api.js # API client (all endpoints) │ ├── styles.css # Full dark/light theme CSS │ ├── utils.js # Shared utilities -│ └── pages/ # 13 page modules +│ └── pages/ # 20 page modules (13 original + 7 v0.2.0) │ ├── dashboard.js # Overview with stats │ ├── skills.js # Skill grid/list/detail │ ├── memory.js # Brain file editor @@ -162,7 +170,14 @@ agentic-os/ │ ├── prompts.js # Template library │ ├── standards.js # Code conventions │ ├── settings.js # Config editor -│ └── setup-wizard.js # Guided setup +│ ├── setup-wizard.js # Guided setup +│ ├── kanban.js # ▸ Kanban Board (v0.2.0) +│ ├── goals.js # ▸ Goals (v0.2.0) +│ ├── journal.js # ▸ Journal (v0.2.0) +│ ├── agent-health.js # ▸ Agent Health (v0.2.0) +│ ├── smart-router.js # ▸ Smart Router (v0.2.0) +│ ├── learning-analytics.js # ▸ Learning Analytics (v0.2.0) +│ └── session-replay.js # ▸ Session Replay (v0.2.0) │ ├── brain/ # Shared context (all agents read) │ ├── business-brain.md # Current project context @@ -170,7 +185,8 @@ agentic-os/ │ ├── recent-decisions.md │ ├── active-projects.md │ ├── identity.md -│ └── constitution.md +│ ├── constitution.md +│ └── journal/ # Daily markdown entries (YYYY-MM-DD.md) │ ├── skills/ # 16 executable skills │ ├── devops-audit/ # GCP/CloudMart infra audit @@ -202,6 +218,27 @@ agentic-os/ --- +## 🆕 What's New in v0.2.0 + +| Feature | Description | +|---------|-------------| +| **📋 Kanban Board** | Visual task management with 6 columns (triage → todo → ready → in_progress → blocked → done), drag-and-drop, priority labels, filtering, and detail modals with complete/block/unblock actions | +| **🎯 Goals** | Create and track project targets with progress bars, categories, and target dates. Auto-syncs to `brain/active-projects.md` for agent awareness | +| **📓 Journal** | Daily markdown journal entries stored as `brain/journal/YYYY-MM-DD.md`. Full-text search, day streak tracking, word count | +| **❤️ Agent Health** | Real-time dashboard showing online/offline status for all 3 agents (opencode, Hermes, Gemini CLI). Auto-refresh every 5 seconds | +| **🧭 Smart Router** | Keyword-based routing engine — type a task description and get an AI-suggested agent with confidence score. Manual override available | +| **📊 Learning Analytics** | Skill evaluation scores, performance trends, and per-skill detail breakdowns with mini bar charts | +| **🎬 Session Replay** | Browse and replay past opencode sessions directly from the dashboard. View message content and timestamps | + +### UI Modernization +- **Glass morphism cards** with subtle backdrop blur +- **Glow borders** and gradient accents on interactive elements +- **Skeleton loaders** with shimmer animation for async content +- **Empty states** with icons and contextual messages +- **All CSS additions are zero-breaking** — existing 13 pages and 28 endpoints unchanged + +--- + ## 🎮 Usage ### AI Chat @@ -222,6 +259,27 @@ Create cron jobs: heartbeat (5 min), memory consolidation (weekly), daily standu ### Cost Analytics Track spending per provider/model/agent. Free-tier alerts warn when nearing limits. +### Kanban Board (v0.2.0) +Drag tasks across columns, filter by priority/category, click to view details. Block tasks when blocked, mark complete when done. + +### Goals (v0.2.0) +Create goals with categories and target dates. Progress tracked via +25% increments. Completed goals auto-sync to brain context. + +### Journal (v0.2.0) +Write daily entries with markdown support. Auto-saves after 2 seconds. Search across all entries from the dashboard. + +### Smart Router (v0.2.0) +Describe a task in plain English — the router analyzes keywords and suggests the best agent. Route manually or let AI decide. + +### Agent Health (v0.2.0) +Monitor online status of all 3 agents in real time with 5-second auto-refresh. Health checks are filesystem-based (no subprocess calls). + +### Learning Analytics (v0.2.0) +View evaluation scores for all 16 skills. Trends chart shows score progression over time. Top skills ranked by performance. + +### Session Replay (v0.2.0) +Browse opencode session logs by date and size. Click "Replay" to view all messages in a chat-like interface. + --- ## 📊 Comparison: Agentic OS vs Claude Agent OS (Julian Goldie) @@ -240,7 +298,7 @@ Track spending per provider/model/agent. Free-tier alerts warn when nearing limi | **Audit Trail** | Not shown | Full activity log | | **Standards System** | Not shown | Discover/inject conventions | | **Client Timeout** | Not shown | 200s AbortController | -| **Kanban Board** | Yes | No (not needed for agent OS) | +| **Kanban Board** | Yes | **Yes — built-in** with drag-and-drop, priority, block/unblock, filters | | **Open Source** | No (tutorial only) | **MIT License** | ---