by OpenCowAI
One task, one agent, delivered. The open-source platform for task-driven autonomous AI agents.OpenCow assigns an autonomous AI agent to every task — features, campaigns, reports, audits — and delivers them in parallel. Full context. Full control. Every department. 🐄
# Add to your Claude Code skills
git clone https://github.com/OpenCowAI/opencowLast scanned: 5/24/2026
{
"issues": [
{
"type": "npm-audit",
"message": "@anthropic-ai/sdk: Claude SDK for TypeScript has Insecure Default File Permissions in Local Filesystem Memory Tool",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@larksuiteoapi/node-sdk: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "@mendable/firecrawl-js: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "@opencow-ai/opencow-agent-sdk: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "axios: Axios has a NO_PROXY Hostname Normalization Bypass that Leads to SSRF",
"severity": "high"
},
{
"type": "npm-audit",
"message": "dompurify: DOMPurify contains a Cross-site Scripting vulnerability",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "gaxios: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "monaco-editor: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "uuid: uuid: Missing buffer bounds check in v3/v5/v6 when buf is provided",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "ws: ws: Uninitialized memory disclosure",
"severity": "medium"
}
],
"status": "WARNING",
"scannedAt": "2026-05-24T07:21:44.536Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}opencow is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by OpenCowAI. One task, one agent, delivered. The open-source platform for task-driven autonomous AI agents.OpenCow assigns an autonomous AI agent to every task — features, campaigns, reports, audits — and delivers them in parallel. Full context. Full control. Every department. 🐄. It has 394 GitHub stars.
opencow returned warnings in SkillsLLM's automated security scan. It has no critical vulnerabilities, but review the flagged issues in the Security Report section before adding it to your workflow.
Clone the repository with "git clone https://github.com/OpenCowAI/opencow" and add it to your Claude Code skills directory (see the Installation section above).
opencow is primarily written in TypeScript. It is open-source under OpenCowAI on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh opencow against similar tools.
No comments yet. Be the first to share your thoughts!
Requires a passing catalog security scan. Resolve the flagged issues and resubmit to enable featuring.
The open-source platform for task-driven autonomous AI. Every task becomes an autonomous agent — campaigns, reports, features, audits ship in parallel. For every team.
How It Works · Features · Quick Start · Architecture · Contributing
Website · X (Twitter) · Download
| Step | What happens |
|---|---|
| Create | Write a task, not a prompt. Describe the deliverable — a campaign, a report, a feature, an audit. OpenCow links full context: project files, prior work, related tasks. |
| Dispatch | One task, one agent. Each task gets a dedicated agent with full context — project knowledge, team playbooks, organizational standards. 15 tasks, 15 agents, in parallel. |
| Deliver | Agents research, draft, build, and publish — autonomously. Real-time progress, instant notifications, approval gates at every step. Review. Ship. |
Everything to turn your task list into a parallel AI workforce.
Built-in task tracker where every task becomes an agent. Break projects into sub-tasks, each with a dedicated agent. Your task list IS your delivery plan.
1 Task = 1 Agent · Sub-task hierarchy · Auto-linked context
Equip agents with your org's knowledge, standards, and tools. Skills, playbooks, integrations — every agent follows your processes.
Custom skills · 6 capability types · Auto-sync standards
Real-time dashboard. Track every agent's progress and actions. Approve deliverables. One screen, full visibility.
Live monitoring · Task-linked status · Approval gates
Dispatch agents from Telegram, Discord, WeChat, or Lark. Schedule recurring workflows. Get notified via webhooks.
4 IM platforms · Natural language · 7 schedule types
No plugins. No integrations to configure. Every capability your AI workforce needs.
Task & Agent Core Task Tracker · Agent DashboardLive Monitor · Multi-Project
Intelligence Intelligence Hub · MarketplaceBuilt-in Browser · Artifacts
Automation Scheduling · WebhooksNotifications · Live Preview
Command & Control IM Command · TerminalCommand Palette · Themes
The design decisions that define OpenCow.
| Principle | What it means | |
|---|---|---|
| 1:1 | Task → Agent | One task, one agent. Full context. Full traceability. Zero ambiguity. |
| ✅ | Local & Private | Everything runs on your machine. Zero telemetry. Zero cloud. Your data never leaves. |
| 15+ | Parallel Agents | Deliver 15+ tasks simultaneously. Suspend and resume any agent without losing context. |
| 4-Layer | Deep Context Engine | Every agent inherits organizational knowledge, project context, team standards, and task-specific instructions. |
Prerequisites: Node.js >= 18 and pnpm >= 9
# Clone the repository
git clone https://github.com/OpenCowAI/opencow.git
cd opencow
# Install dependencies
pnpm install
# Launch in development mode (HMR enabled)
pnpm dev
Grab the latest release from opencow.ai/download — free, open source, ready in 60 seconds.
| Layer | Choice | Why |
|---|---|---|
| Desktop | Electron 40 | Cross-platform, native-grade experience |
| UI | React 19 + Tailwind CSS 4 | Concurrent rendering, utility-first styling |
| Language | TypeScript (strict, zero any) |
End-to-end type safety |
| State | Zustand | Lightweight reactive stores with row-level subscriptions |
| Build | electron-vite (Vite) | Sub-second HMR, triple-target build |
| Database | SQLite via Kysely | Local-first, type-safe schema with 35+ migrations |
| Terminal | xterm.js + WebGL | Hardware-accelerated terminal rendering |
| Editor | Monaco Editor | VS Code-grade editing experience |
| Testing | Vitest + React Testing Library | Fast, modern test runner |
| AI | Claude Agent SDK + Codex SDK + MCP | Multi-engine — choose Claude or Codex as your AI engine, with Model Context Protocol |
OpenCow follows a hardened Electron architecture with strict process isolation:
┌─────────────────────────────────────────────────────┐
│ Renderer Process │
│ ┌───────────┐ ┌──────────┐ ┌──────────────────┐ │
│ │ React 19 │ │ Zustand │ │ 271 Components │ │
│ │ Components │ │ Stores │ │ 68 Hooks │ │
│ └─────┬─────┘ └────┬─────┘ └────────┬─────────┘ │
│ └──────────────┴─────────────────┘ │
│ │ IPC (contextBridge) │
├────────────────────────┼────────────────────────────┤
│ Main Process │
│ ┌──────────┐ ┌──────────┐ ┌───────────────────┐ │
│ │ DataBus │ │ Services │ │ Native Modules │ │
│ │ Events │ │ (47+) │ │ SQLite · PTY │ │
│ └──────────┘ └──────────┘ └───────────────────┘ │
│ ┌──────────┐ ┌──────────┐ ┌───────────────────┐ │
│ │ Claude │ │ Bot │ │ Capability │ │
│ │ Agent SDK│ │ Gateway │ │ Center │ │
│ └──────────┘ └──────────┘ └───────────────────┘ │
└─────────────────────────────────────────────────────┘
Security model:
contextIsolation: true — renderer cannot access Node.jsnodeIntegration: false — no direct module loadingcontextBridge.exposeInMainWorld~/.opencow-dev) and production (~/.opencow)opencow/
├── electron/ # Main process
│ ├── main.ts # App entry point
│ ├── preload.ts # Secure IPC bridge
│ ├── services/ # 47+ backend service modules
│ │ ├── capabilityCenter/ # AI capability management
│ │ ├── schedule/ # Cron automation engine
│ │ ├── messaging/ # Multi-channel messaging
│ │ ├── git/ # Git integration layer
│ │ └── ...
│ ├── database/ # SQLite schema & migrations
│ ├── sources/ # Hook, task, and stats data sources
│ └── ipc/ # IPC channel handlers
├── src/
│ ├── renderer/ # React application
│ │ ├── components/ # 32 feature modules, 271 components
│ │ ├── hooks/ # 68 custom React hooks
│ │ ├── stores/ # 18 Zustand domain stores
│ │ ├── lib/ # Utilities & helpers
│ │ └── locales/ # i18n (en-US, zh-CN)
│ └── shared/ # Cross-process types & utilities
├── tests/ # Vitest test suite
├── docs/ # 520+ design docs & proposals
└── resources/ # App icons & tray assets
| Command | What it does |
|---|---|
pnpm dev |
Start with HMR |
pnpm build |
Compile all targets |
pnpm preview |
Build + launch in production mode |
pnpm package |
Build + package .app (fast, for testing) |
pnpm package:dmg |
Build + package .dmg installer |
pnpm typecheck |
TypeScript strict check |
pnpm lint |
ESLint |
pnpm format |
Prettier |
pnpm test |
Run all tests |
pnpm test:watch |
Watch mode |
electron-vite compiles three independent TypeScript targets:
| Target | Entry | Output |
|---|---|---|
| Main | electron/main.ts |
out/main/ |
| Preload | electron/preload.ts |
out/preload/ |
| Renderer | src/renderer/index.html |
out/renderer/ |
@ → src/renderer (renderer only)@shared → src/shared (all targets)any usagefeat:, fix:, perf:, refactor:, etc.# macOS .app (for local testing, fast)
pnpm package
# Output: dist/mac-arm64/OpenCow.app
# macOS .dmg (for distribution)
pnpm package:dmg
# Output: dist/OpenCow-{version}.dmg
Cross-platform builds for Windows and Linux are supported via electron-builder configuration in