Skip to content
Back to search

agentic-os

SkillWorks with Gemini CLIGitHub

Agentic OS: Multi-agent orchestration platform for opencode, Hermes & Gemini CLI. Skills hub, scheduler, cost analytics, memory & backup.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/modimihir07-agentic-os/badge.svg)](/listings/modimihir07-agentic-os)

HTML

<a href="/listings/modimihir07-agentic-os"><img src="/api/listings/modimihir07-agentic-os/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

git clone https://github.com/modimihir07/agentic-os.git
cd agentic-os
chmod +x install.sh && ./install.sh
./start.sh
# Open http://127.0.0.1:8080

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 417 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <br/>
  3. <img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="License: MIT"/>
  4. <img src="https://img.shields.io/badge/python-3.10+-blue.svg" alt="Python 3.10+"/>
  5. <img src="https://img.shields.io/badge/FastAPI-0.115+-green.svg" alt="FastAPI"/>
  6. <img src="https://img.shields.io/badge/agents-3-orange.svg" alt="3 Agents"/>
  7. <img src="https://img.shields.io/badge/skills-15-purple.svg" alt="15 Skills"/>
  8. <img src="https://img.shields.io/badge/version-v4.0-blueviolet.svg" alt="v4.0"/>
  9. <img src="https://img.shields.io/badge/status-stable-brightgreen.svg" alt="Status: Stable"/>
  10. <a href="https://dev.to/mihir_nmodi_14a06a4019e1/i-built-an-open-source-agent-os-2h30"><img src="https://img.shields.io/badge/dev.to-article-blue.svg" alt="dev.to article"/></a>
  11. <br/><br/>
  12. </div>
  13. # Agentic OS (agentic-os) 🧠 — Multi-Agent Orchestration Platform
  14. A locally-hosted operating system for AI agents — an open-source GitHub repository — that coordinates **opencode**, **Hermes Agent**, and **agy CLI** into a unified dashboard with persistent memory, cron scheduling, skill execution, cost analytics, and disaster recovery.
  15. > **Why Agentic OS?** Most agent tools work in isolation — a terminal for coding, a separate chat for research, another for memory. Agentic OS is the **control plane** that unifies them: one dashboard, one memory layer, one scheduler, one skill hub. Three agents, infinite capabilities.
  16. ---
  17. ## ✨ Features
  18. | Category | Features |
  19. |----------|----------|
  20. | **🤖 3-Agent Engine** | opencode (code/DevOps), Hermes (memory/scheduling), agy (research/analysis) with intelligent routing |
  21. | **🧩 15+ Skills** | Executable skill packs with eval scoring, learnings, and score history per run |
  22. | **🧠 Persistent Memory** | SQLite FTS5 + `brain/` folder — shared context read by all agents at session start |
  23. | **⏱ Cron Scheduler** | APScheduler-powered jobs — heartbeat, memory consolidation, daily standup, DevOps audit |
  24. | **💰 Cost Analytics** | Track spending per provider, model, agent. Free-tier alerts prevent surprise bills |
  25. | **📋 Audit Trail** | Every action logged — chat, skill runs, settings changes, backups |
  26. | **💾 One-Click Backup** | Full tar.gz snapshot of all configs, skills, brain, agents, prompts |
  27. | **📝 Prompt Library** | 10 reusable templates — code review, system audit, project plan, brainstorm, and more |
  28. | **📐 Standards System** | Discover and inject coding conventions across your project |
  29. | **🔌 Plugin Registry** | Marketplace-style plugin management (extensible via skills) |
  30. | **🎨 Dark/Light Theme** | GitHub-style dark mode + clean light theme, toggle from sidebar |
  31. | **⚡ Zero API Costs** | Built for free tiers — Antigravity (agy), OpenRouter free models, local opencode |
  32. | **📋 Kanban Board** | Visual task management — drag-and-drop columns, priority/status filtering, block/unblock, detail view |
  33. | **🎯 Goals** | Project targets with progress tracking, auto-syncs to `brain/active-projects.md` |
  34. | **📓 Journal** | Daily markdown entries stored as `brain/journal/YYYY-MM-DD.md` with full-text search |
  35. | **❤️ Agent Health** | Real-time monitoring of opencode, Hermes, and agy CLI availability |
  36. | **🧭 Smart Router** | Keyword-based task routing with confidence scoring — suggests best agent for any task |
  37. | **📊 Learning Analytics** | Skill evaluation scores, performance trends, and historical charts |
  38. | **🎬 Session Replay** | Browse and replay past opencode sessions from the dashboard |
  39. | **⚠ Error Dashboard** | Real-time error tracking with category filtering and circuit breaker status |
  40. | **🔌 Circuit Breaker** | Auto-trip after N failures, auto-recovery after 300s, manual reset |
  41. | **⏱ Event-Driven Scheduler** | File-watcher auto-reloads jobs on change, webhook receiver, execution history |
  42. | **🔗 Webhook Receiver** | `/api/webhook` — trigger skill execution from external tools |
  43. | **🧠 SQLite FTS5 Memory** | Full-text search across brain, skills, journal with entity extraction |
  44. | **🤖 Auto-Skill Generator** | `POST /api/skills/generate` — create SKILL.md from natural language |
  45. | **📱 Mobile PWA** | Bottom navigation bar, manifest.json, service worker, touch-friendly UI |
  46. ---
  47. ## 🏗 Architecture
  48. ```
  49. ┌──────────────────────────────────────────────────────────┐
  50. │ AGENTIC OS DASHBOARD │
  51. │ FastAPI + Tailwind SPA │
  52. ├──────────────────────────────────────────────────────────┤
  53. │ │
  54. │ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │
  55. │ │ opencode │ │ Hermes │ │ agy CLI │ │
  56. │ │ (Code/DevOps)│ │(Memory/Sched)│ │ (Research/ │ │
  57. │ │ (File Ops) │ │ (/Channels) │ │ Analysis) │ │
  58. │ └──────────────┘ └──────────────┘ └──────────────┘ │
  59. │ │
  60. │ ┌────────────────────────────────────────────────────┐ │
  61. │ │ 7 CORE LAYERS (Stacked) │ │
  62. │ │ Layer 7: Identity / Persona / Constitution │ │
  63. │ │ Layer 6: Self-Evolution + Capability Manager │ │
  64. │ │ Layer 5: Scheduler + Awareness + Health Guardian │ │
  65. │ │ Layer 4: Memory Graph + Memory Consolidation │ │
  66. │ │ Layer 3: Skills Hub + Eval + Learnings Loop │ │
  67. │ │ Layer 2: Business Brain + Context Folders │ │
  68. │ │ Layer 1: Agent Router + Standards + Profiles │ │
  69. │ └────────────────────────────────────────────────────┘ │
  70. └──────────────────────────────────────────────────────────┘
  71. ```
  72. ### Agent Responsibilities
  73. | Agent | Role | Default Model | Provider | Cost |
  74. |-------|------|---------------|----------|------|
  75. | **opencode** | Code generation, DevOps, file operations | deepseek-v4-flash-free | opencode-zen | **$0** |
  76. | **Hermes Agent** | Persistent memory, scheduling, messaging | Owl Alpha (1M ctx) | OpenRouter | **$0** |
  77. | **agy CLI** | Web research, multi-modal analysis | Antigravity | agy CLI | **$0** |
  78. ### Routing Rules
  79. - **Code/DevOps task?** → opencode
  80. - **Memory/Channel/Schedule?** → Hermes Agent
  81. - **Research/Analysis?** → agy CLI
  82. - **Complex multi-step?** → Chain: agy researches → opencode implements → Hermes monitors/schedules
  83. ---
  84. ## 🚀 Quick Start
  85. ```bash
  86. git clone https://github.com/modimihir07/agentic-os.git
  87. cd agentic-os
  88. chmod +x install.sh && ./install.sh
  89. ./start.sh
  90. # Open http://127.0.0.1:8080
  91. ```
  92. ---
  93. ## 📋 Prerequisites
  94. | Tool | Required? | Install |
  95. |------|-----------|---------|
  96. | Python 3.10+ | ✅ Required | Auto-installed via `uv` by `install.sh` |
  97. | Node.js 18+ | ⚠ For opencode | `curl -fsSL https://deb.nodesource.com/setup_20.x \| sudo bash - && sudo apt install -y nodejs` |
  98. | opencode | ⚠ For code tasks | `npm install -g @opencode/cli` |
  99. | Hermes Agent | ⚠ For memory/scheduling | `curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh \| bash` |
  100. | agy CLI | ⚠ For research/analysis | `curl -fsSL https://antigravity.ai/install \| bash` |
  101. > ⚠ = Optional — the dashboard works with any subset of installed agents.
  102. ---
  103. ## 🔧 Configuration
  104. ### Hermes (OpenRouter)
  105. ```bash
  106. # Set your OpenRouter API key
  107. echo 'OPENROUTER_API_KEY=sk-or-v1-your-key-here' > ~/.hermes/.env
  108. ```
  109. ### agy CLI (Antigravity)
  110. ```bash
  111. agy login
  112. # Authenticate to enable web research, analysis, and document understanding
  113. ```
  114. ### Dashboard Settings
  115. Edit `data/settings.json`:
  116. ```json
  117. {
  118. "dashboard": { "port": 8080 },
  119. "theme": "dark",
  120. "agents": { "opencode": true, "hermes": true, "agy": true }
  121. }
  122. ```
  123. ---
  124. ## 📁 Project Structure
  125. ```
  126. agentic-os/
  127. ├── server.py # FastAPI backend (REST API)
  128. ├── requirements.txt # Python dependencies
  129. ├── install.sh # One-command installer
  130. ├── start.sh # Launch dashboard
  131. ├── backup.sh / restore.sh # Disaster recovery
  132. │
  133. ├── dashboard/ # Web frontend (SPA)
  134. │ ├── index.html # Entry point + sidebar
  135. │ ├── app.js # SPA router + theme/sidebar toggle
  136. │ ├── api.js # API client (all endpoints)
  137. │ ├── styles.css # Full dark/light theme CSS
  138. │ ├── utils.js # Shared utilities
  139. │ └── pages/ # 22 page modules (13 original + 7 v2.0 + 1 v3.0 + 1 v4.0)
  140. │ ├── dashboard.js # Overview with stats
  141. │ ├── skills.js # Skill grid/list/detail
  142. │ ├── memory.js # Brain file editor + Knowledge Graph
  143. │ ├── chat.js # Multi-agent chat + file attachments
  144. │ ├── history.js # ▸ Chat History Search (v4.0)
  145. │ ├── scheduler.js # Cron job manager
  146. │ ├── audit.js # Activity trail
  147. │ ├── cost.js # Cost analytics charts
  148. │ ├── plugins.js # Plugin marketplace
  149. │ ├── backups.js # Backup/restore UI
  150. │ ├── prompts.js # Template library
  151. │ ├── standards.js # Code conventions
  152. │ ├── settings.js # Config editor
  153. │ ├── setup-wizard.js # Guided setup
  154. │ ├── kanban.js # ▸ Kanban Board (v2.0)
  155. │ ├── goals.js # ▸ Goals (v2.0)
  156. │ ├── journal.js # ▸ Journal (v2.0)
  157. │ ├── agent-health.js # ▸ Agent Health (v2.0)
  158. │ ├── smart-router.js # ▸ Smart Router (v2.0)
  159. │ ├── learning-analytics.js # ▸ Learning Analytics (v2.0)
  160. │ ├── session-replay.js # ▸ Session Replay (v2.0)
  161. │ └── errors.js # ▸ Error Dashboard (v3.0)
  162. │
  163. ├── brain/ # Shared context (all agents read)
  164. │ ├── memory_search.py # ▸ SQLite FTS5 search (v3.0)
  165. │ ├── business-brain.md # Current project context
  166. │ ├── memory.md # Accumulated knowledge
  167. │ ├── recent-decisions.md
  168. │ ├── active-projects.md
  169. │ ├── identity.md
  170. │ ├── constitution.md
  171. │ └── journal/ # Daily markdown entries (YYYY-MM-DD.md)
  172. │
  173. ├── skills/ # 15 executable skills
  174. │ ├── devops-audit/ # GCP/CloudMart infra audit
  175. │ ├── heartbeat/ # 5-min health check
  176. │ ├── content-draft/ # Blog/newsletter writing
  177. │ ├── code-review/ # PR review checklist
  178. │ ├── research-synthesis/ # agy research aggregator
  179. │ ├── daily-standup/ # Morning briefing
  180. │ ├── meeting-minutes/ # Notes processor
  181. │ ├── project-planner/ # Step-by-step plans
  182. │ ├── brainstorming/ # Socratic design
  183. │ ├── systematic-debug/ # 4-phase root cause
  184. │ ├── memory-consolidation/ # Weekly synthesis
  185. │ ├── backup-skill/ # Snapshot creator
  186. │ ├── cost-analytics/ # Multi-provider cost
  187. │ ├── tdd-cycle/ # Red-green-refactor
  188. │ ├── goal-planner/ # Goal → steps
  189. │ └── _template/ # Starter template
  190. │
  191. ├── agents/ # Per-agent configs (opencode, hermes, agy)
  192. ├── scheduler/jobs/ # Cron job definitions
  193. ├── registry/ # Plugin marketplace
  194. ├── standards/ # Discover/inject conventions
  195. ├── prompts/ # 10 reusable templates
  196. ├── data/ # Runtime data (agent-routes.json tracked; settings/cost/chat/error/scheduler/memory/circuit/kanban/uploads gitignored)
  197. ├── audit/ # Activity log (gitignored)
  198. └── backups/ # Snapshots (gitignored)
  199. ```
  200. ---
  201. ## 🆕 What's New in v4.0
  202. | Feature | Description |
  203. |---------|-------------|
  204. | **🤖 agy (Antigravity) replaces Gemini CLI** | Full provider swap across backend, routing, frontend, skills, agents/, and docs. `data/agent-routes.json`, circuit breaker, health checks, chat all use `agy` |
  205. | **🛡 Port Conflict Auto-Kill** | `start.sh` detects a stale dashboard process on the target port and kills it before starting |
  206. | **📦 Auto-Install apscheduler** | `scheduler.py` auto-installs missing dependencies instead of failing on startup |
  207. | **💬 Chat History Search** | `/api/chat/history` supports `q`, `agent`, `limit` filters + a dedicated History page with search, agent filter pills, and date grouping |
  208. | **📎 Chat File Attachments** | `POST /api/chat/upload` (multipart) accepts text files up to 2 MB (validated allowlist), previews content to the agent, and stores under `data/uploads/` with 24h TTL cleanup |
  209. | **🕸 Memory Knowledge Graph** | `GET /api/memory/graph` returns nodes (brain/skills/journal docs + extracted entities) and edges (shares_source / mentions), rendered as an interactive Canvas graph in the Memory page |
  210. | **📜 Code Diff Viewer** | `GET /api/diff?file=&ref=` returns unified git diff with repo-relative path-traversal protection; "View Diff" button on the Skills page |
  211. | **🧪 15 new tests** | Suite grows from 59 → 74 isolated tests covering chat history, uploads, memory graph, and diff viewer |
  212. | **🛠 Stale-Cache Elimination** | `no-store` cache headers on all dashboard assets, `?v=` cache-busting, service-worker purge on load, root-level asset fallbacks so stale index.html never breaks the UI |
  213. | **📐 Zoom-Proof Layout** | Content width capped at 1600px, responsive file-card grid, and `flex-shrink: 0` on tab bars — layout stays clean from 60% to 100% zoom |
  214. | **🔢 Correct Skill Count** | Skills badge now counts skill directories (15) via the status endpoint instead of returning 0 |
  215. During the v4.0 hardening pass the following **layout & caching bugs** were crushed: tab bars (Files/Knowledge Graph, Grid/List) collapsing to 1px under content at certain zooms, oversized cards stretching to 3500px+ at 50% zoom, cached index.html referencing dead asset URLs, and the sidebar Skills badge showing 0.
  216. ---
  217. ## 🆕 What's New in v3.0
  218. | Feature | Description |
  219. |---------|-------------|
  220. | **🔒 Security Audit** | 23 vulnerabilities fixed: 3 CRITICAL (path traversal), 8 HIGH (XSS, command injection, missing headers), 7 MEDIUM. Security headers middleware added (CSP, HSTS, X-Frame-Options) |
  221. | **⏱ Event-Driven Scheduler** | Rewritten with file-watcher auto-reload (watchdog-style), webhook receiver at `/api/webhook`, execution history, manual job triggers |
  222. | **⚠ Error Dashboard** | New `/api/errors` endpoints with category filtering (agent/skill/api/system). Dedicated dashboard page with error log + circuit breaker status cards |
  223. | **🔌 Circuit Breaker** | Auto-trip after 3 failures, half-open recovery after 300s. Per-agent state tracking with manual reset. Prevents cascading failures to offline agents |
  224. | **🧠 Persistent Memory (SQLite FTS5)** | Full-text search across `brain/*.md`, `skills/*/*.md`, `brain/journal/`. Entity extraction (persons, emails, URLs, acronyms, IPs). Reindex endpoint |
  225. | **🤖 Auto-Skill Generator** | `POST /api/skills/generate` takes natural language description → creates full SKILL.md with eval.json and context folder |
  226. | **🔗 Webhook Receiver** | Generic webhook at `/api/webhook/generic` plus skill-targeted webhooks. Integrates with GitHub, CI/CD, external tools |
  227. | **📱 Mobile PWA** | Bottom navigation bar, `manifest.json`, service worker (offline fallback), PWA meta tags, touch-friendly 16px inputs, responsive grid collapse |
  228. ### Security Hardening
  229. - **Path traversal**: All file endpoints validate `..` and `/` in user-supplied names
  230. - **XSS elimination**: 19 violations fixed across 7 JS files — all `onclick` handlers use `encodeURIComponent`, all text uses `escapeHtml()`
  231. - **Security headers**: CSP, HSTS, X-Frame-Options, X-Content-Type-Options, Referrer-Policy
  232. - **CORS restricted**: Only `http://127.0.0.1:8080` and `http://localhost:8080`
  233. - **API keys masked**: `/api/settings` returns keys as masked values (e.g., `sk-o****`)
  234. - **Input validation**: Chat messages limited to 10K chars, brain/skill names reject special chars
  235. - **Session replay**: Content limited to 2000 chars, path traversal prevented
  236. - **Runtime data gitignored**: `error-log.json`, `circuit-breaker.json`, `scheduler-history.json`, `memory.db`, `kanban/*.json`
  237. ---
  238. ## 🆕 What's New in v2.0
  239. | Feature | Description |
  240. |---------|-------------|
  241. | **📋 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 |
  242. | **🎯 Goals** | Create and track project targets with progress bars, categories, and target dates. Auto-syncs to `brain/active-projects.md` for agent awareness |
  243. | **📓 Journal** | Daily markdown journal entries stored as `brain/journal/YYYY-MM-DD.md`. Full-text search, day streak tracking, word count |
  244. | **❤️ Agent Health** | Real-time dashboard showing online/offline status for all 3 agents (opencode, Hermes, agy CLI). Auto-refresh every 5 seconds |
  245. | **🧭 Smart Router** | Keyword-based routing engine — type a task description and get an AI-suggested agent with confidence score. Manual override available |
  246. | **📊 Learning Analytics** | Skill evaluation scores, performance trends, and per-skill detail breakdowns with mini bar charts |
  247. | **🎬 Session Replay** | Browse and replay past opencode sessions directly from the dashboard. View message content and timestamps |
  248. ### UI Modernization
  249. - **Glass morphism cards** with subtle backdrop blur
  250. - **Glow borders** and gradient accents on interactive elements
  251. - **Skeleton loaders** with shimmer animation for async content
  252. - **Empty states** with icons and contextual messages
  253. - **All CSS additions are zero-breaking** — existing 13 pages and 28 endpoints unchanged
  254. ---
  255. ## 🎮 Usage
  256. ### AI Chat
  257. Select an agent from the sidebar → type your message → get response.
  258. | Agent | Best for | Example |
  259. |-------|----------|---------|
  260. | **opencode** | "Check system status", "Deploy to GKE" | Code + terminal automation |
  261. | **Hermes** | "What did I work on recently?", "Schedule a daily backup" | Memory recall, scheduling |
  262. | **agy** | "Research latest AI agent trends", "Analyze this image" | Web research, multi-modal |
  263. ### Skills
  264. Browse 15 skills from Skills Hub → click Run → monitor eval scores over time.
  265. ### Scheduler
  266. Create cron jobs: heartbeat (5 min), memory consolidation (weekly), daily standup, DevOps audit.
  267. ### Cost Analytics
  268. Track spending per provider/model/agent. Free-tier alerts warn when nearing limits.
  269. ### Kanban Board (v2.0)
  270. Drag tasks across columns, filter by priority/category, click to view details. Block tasks when blocked, mark complete when done.
  271. ### Goals (v2.0)
  272. Create goals with categories and target dates. Progress tracked via +25% increments. Completed goals auto-sync to brain context.
  273. ### Journal (v2.0)
  274. Write daily entries with markdown support. Auto-saves after 2 seconds. Search across all entries from the dashboard.
  275. ### Smart Router (v2.0)
  276. Describe a task in plain English — the router analyzes keywords and suggests the best agent. Route manually or let AI decide.
  277. ### Agent Health (v2.0)
  278. Monitor online status of all 3 agents in real time with 5-second auto-refresh. Health checks are filesystem-based (no subprocess calls).
  279. ### Learning Analytics (v2.0)
  280. View evaluation scores for all 15 skills. Trends chart shows score progression over time. Top skills ranked by performance.
  281. ### Session Replay (v2.0)
  282. Browse opencode session logs by date and size. Click "Replay" to view all messages in a chat-like interface.
  283. ### Error Dashboard (v3.0)
  284. View system errors grouped by category (agent, skill, API, system). Filter by category, clear all errors. Circuit breaker cards show per-agent failure state — reset from the dashboard.
  285. ### Event-Driven Scheduler (v3.0)
  286. Jobs auto-reload when JSON files in `scheduler/jobs/` change. Trigger skills via webhooks at `POST /api/webhook` with `{"skill": "skill-name", "payload": {...}}`. Manual trigger at `/api/scheduler/trigger/{job_id}`.
  287. ### Persistent Memory Search (v3.0)
  288. Full-text search across all brain files, skills, and journal entries via SQLite FTS5. Query at `GET /api/memory/search?q=...` with highlighted snippets. Reindex at `POST /api/memory/reindex`. Entities (persons, emails, URLs) auto-extracted.
  289. ### Auto-Skill Generator (v3.0)
  290. Create new skills from natural language: `POST /api/skills/generate` with `{"name": "my-skill", "description": "Does X by doing Y"}`. Generates SKILL.md, eval.json, learnings.md, and context folder.
  291. ### Webhooks (v3.0)
  292. `POST /api/webhook` — trigger any skill by name. `POST /api/webhook/generic` — catch-all for external tool integration (GitHub, CI/CD, etc.).
  293. ### Mobile PWA (v3.0)
  294. Open Agentic OS on your phone — bottom nav bar replaces sidebar, touch targets are 44px+, service worker caches assets. Add to home screen for app-like experience.
  295. ---
  296. ## 📊 Comparison: Agentic OS vs Claude Agent OS (Julian Goldie)
  297. | Feature | Claude Agent OS (Video) | Agentic OS (This Project) |
  298. |---------|------------------------|---------------------------|
  299. | **Core Agents** | Claude + OpenClaw + Hermes | opencode + Hermes + agy CLI |
  300. | **Cost** | $20/mo (Claude subscription) | **$0 — all free tiers** |
  301. | **Stack** | Next.js + Tailwind | FastAPI + vanilla JS SPA |
  302. | **Architecture** | 4 layers | **7 layers** |
  303. | **Skills System** | Plugin marketplace (2,000+ from Hermes) | 15 curated skills + eval scoring + learnings |
  304. | **Memory** | Obsidian vault (external) | Built-in brain/ + SQLite FTS5 |
  305. | **Scheduler** | Not shown | APScheduler cron jobs |
  306. | **Cost Tracking** | Not shown | Built-in per-provider analytics |
  307. | **Backup/Restore** | Not shown | One-click tar.gz snapshots |
  308. | **Audit Trail** | Not shown | Full activity log |
  309. | **Standards System** | Not shown | Discover/inject conventions |
  310. | **Client Timeout** | Not shown | 200s AbortController |
  311. | **Kanban Board** | Yes | **Yes — built-in** with drag-and-drop, priority, block/unblock, filters |
  312. | **Open Source** | No (tutorial only) | **MIT License** |
  313. ---
  314. ## 🧪 Tested On
  315. - **OS**: Linux (Ubuntu 22.04+), macOS
  316. - **Python**: 3.10, 3.11, 3.12
  317. - **Browsers**: Chrome, Firefox, Edge
  318. - **Agents**: opencode v0.8+, Hermes Agent v1.0+, agy CLI (Antigravity)
  319. ---
  320. ## 🤝 Contributing
  321. 1. Fork the repo
  322. 2. Create a feature branch (`git checkout -b feature/amazing-feature`)
  323. 3. Commit your changes (`git commit -m 'Add amazing feature'`)
  324. 4. Push (`git push origin feature/amazing-feature`)
  325. 5. Open a Pull Request
  326. See `data/agent-routes.json` for routing rules and `skills/_template/` for creating new skills.
  327. ---
  328. ## 📄 License
  329. MIT License — free to use, modify, and distribute.
  330. ---
  331. <div align="center">
  332. <p><strong>Agentic OS</strong> — Built with ❤️ by <a href="https://github.com/modimihir07">Mihir Modi</a></p>
  333. <p>
  334. <a href="https://dev.to/mihir_nmodi_14a06a4019e1/i-built-an-open-source-agent-os-2h30">📖 Read the dev.to article</a>
  335. ·
  336. <a href="https://github.com/modimihir07/agentic-os/issues">Report Bug</a>
  337. ·
  338. <a href="https://github.com/modimihir07/agentic-os/discussions">Discussions</a>
  339. ·
  340. <a href="https://github.com/modimihir07/agentic-os">GitHub</a>
  341. </p>
  342. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.