opencow
OpenCow helps teams get more done by turning everyday tasks into automated projects. Imagine needing a marketing campaign, a financial report, or a new feature built – instead of manually assigning and managing each step, OpenCow creates a dedicated "agent" for each task. These agents use existing company knowledge and processes to research, draft, and deliver results autonomously, keeping everyone informed along the way. Business managers, project leads, and teams struggling with workload bottlenecks would find OpenCow particularly useful. Its unique ability to break down large projects into parallel, self-managed tasks significantly speeds up delivery and improves overall efficiency.
README
<div align="center"> <p align="right"> <strong>English</strong> · <a href="README.zh-CN.md">简体中文</a> </p> <img src="src/renderer/assets/opencow-ip.png" alt="OpenCow" width="160" /> # OpenCow ### One Task. One Agent. Delivered. The open-source platform for task-driven autonomous AI.<br/> Every task becomes an autonomous agent — campaigns, reports, features, audits<br/> ship in parallel. For every team. [](LICENSE) [](https://www.electronjs.org/) [](https://react.dev/) [](https://www.typescriptlang.org/) [](CONTRIBUTING.md) [How It Works](#how-it-works) · [Features](#the-platform) · [Quick Start](#quick-start) · [Architecture](#architecture) · [Contributing](#contributing) **[Website](https://opencow.ai)** · **[X (Twitter)](https://x.com/OpenCow_AI)** · **[Download](https://opencow.ai/download)** </div> --- <div align="center"> <img src="resources/issues-preview-light.png" alt="OpenCow Issues Preview" width="820" /> </div> ## How It Works ### Task In. Result Out. | 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. | --- ## The Platform Everything to turn your task list into a parallel AI workforce. <table> <tr> <td width="50%"> ### Task-to-Agent Pipeline 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` </td> <td width="50%"> ### Agent Intelligence 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` </td> </tr> <tr> <td> ### Agent Command Center Real-time dashboard. Track every agent's progress and actions. Approve deliverables. One screen, full visibility. `Live monitoring` · `Task-linked status` · `Approval gates` </td> <td> ### Work from Anywhere Dispatch agents from Telegram, Discord, WeChat, or Lark. Schedule recurring workflows. Get notified via webhooks. `4 IM platforms` · `Natural language` · `7 schedule types` </td> </tr> </table> --- ## Everything. Built In. No plugins. No integrations to configure. Every capability your AI workforce needs. <table> <tr> <td width="25%" align="center"> **Task & Agent Core** <br/><sub>Task Tracker · Agent Dashboard<br/>Live Monitor · Multi-Project</sub> </td> <td width="25%" align="center"> **Intelligence** <br/><sub>Intelligence Hub · Marketplace<br/>Built-in Browser · Artifacts</sub> </td> <td width="25%" align="center"> **Automation** <br/><sub>Scheduling · Webhooks<br/>Notifications · Live Preview</sub> </td> <td width="25%" align="center"> **Command & Control** <br/><sub>IM Command · Terminal<br/>Command Palette · Themes</sub> </td> </tr> </table> --- ## Built Different 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. | --- ## Quick Start ### From source (for contributors) **Prerequisites:** [Node.js](https://nodejs.org/) >= 18 and [pnpm](https://pnpm.io/) >= 9 ```bash # 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 ``` ### Download the app Grab the latest release from [opencow.ai/download](https://opencow.ai/download) — free, open source, ready in 60 seconds. --- ## Tech Stack | 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 | --- ## Architecture 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.js - `nodeIntegration: false` — no direct module loading - Type-safe IPC bridge via `contextBridge.exposeInMainWorld` - Sandboxed file access with explicit path allowlists - Separate data directories for dev (`~/.opencow-dev`) and production (`~/.opencow`) --- ## Project Structure ``` 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 [truncated…]
PUBLIC HISTORY
IDENTITY
Identity inferred from code signals. No PROVENANCE.yml found.
Is this yours? Claim it →METADATA
README BADGE
Add to your README:
