agent-dashboardagent-osagentic-osai-agentsautonomous-agentscost-analyticsdevopsfastapigemini-clihermes-agentmulti-agent-orchestrationopen-sourceopencodeskills-hubtask-orchestration
- Complete CSS redesign with glassmorphism, gradients, animations - All 12 SPA pages rewritten with working forms, modals, charts - Fixed server.py static file serving for dashboard assets - Enhanced utils: modal system, toast with icons, skeletons - Dashboard: stat cards, agent status, activity feed, quick run - Skills: grid/list views, filter, detail with performance chart - Memory: browse/edit brain files inline - Scheduler: CRUD jobs with cron input - Audit: filterable log viewer - Cost: Chart.js agent/time charts, test recording, free-tier alerts - Plugins: registry browser with install flow - Backups: create/restore with confirmation dialog - Prompts: card grid with preview, copy-to-clipboard - Standards: index + detail cards, pattern discovery - Settings: agent toggle, API keys, free-tier limits, dark mode - Setup Wizard: 4-step guided configuration |
||
|---|---|---|
| agents | ||
| audit | ||
| backups | ||
| brain | ||
| dashboard | ||
| data | ||
| prompts | ||
| registry | ||
| scheduler | ||
| skills | ||
| standards | ||
| .gitignore | ||
| AGENTS.md | ||
| README.md | ||
| backup.sh | ||
| install.sh | ||
| requirements.txt | ||
| restore.sh | ||
| server.py | ||
| start.sh | ||
README.md
Agentic OS
A multi-agent orchestration platform that coordinates opencode, Hermes Agent, and Gemini CLI into a unified, self-improving, autonomous work operating system.
Quick Start
chmod +x install.sh && ./install.sh
Architecture
3 agents + 7 layers + web dashboard:
| Agent | Role |
|---|---|
| opencode | Code generation, DevOps, file operations |
| Hermes Agent | Memory, scheduling, channels |
| Gemini CLI | Research, analysis, multi-modal |
Features
- 51 features from top agentic OS implementations
- 10 extra features (cost analytics, git versioning, backup, prompts, etc.)
- Interactive web dashboard (FastAPI + SPA)
- One-click skill execution
- Scheduled workflows
- Persistent memory across sessions
- Self-improving skills with eval scoring
- Multi-agent routing and handoff
- Cost tracking with free-tier alerts
Dashboard
./start.sh
# Visit http://127.0.0.1:8080
License
MIT