Retour au classement

composio-community/open-claude-cowork

JavaScript

Open Source version of Claude Cowork with 500+ SaaS app integrations

anthropicanthropic-claudeclaude-codeclaude-coworkopencodeworkflow-automationaiagentseclectron-app
Croissance des étoiles
Étoiles
4.3k
Forks
741
Croissance hebdomadaire
Issues
6
4.3k4.3k4.3k4.3k4.3k
18 juil.19 juil.20 juil.21 juil.
Artefactsnpmnpm install open-claude-cowork
README

Open Claude Cowork

Secure Clawdbot Demo

Composio Claude Agent SDK Claude Code Twitter

An open-source desktop chat application powered by Claude Agent SDK and Composio Tool Router. Automate your work end-to-end across desktop and all your work apps in one place.

Get your free API key to get started →

Pst. hey, you, join our stargazers :)
GitHub stars


What's Inside

This repo includes two powerful AI tools:

Open Claude Cowork 🦑 Secure Clawdbot
What Full-featured desktop chat interface Personal AI assistant on messaging
Where macOS, Windows, Linux WhatsApp, Telegram, Signal, iMessage
Best for Work automation, multi-chat sessions On-the-go AI access, reminders, memory

Both include 500+ app integrations via Composio (Gmail, Slack, GitHub, Google Drive, and more).


Quick Start

Open Claude Cowork

git clone https://github.com/ComposioHQ/open-claude-cowork.git
cd open-claude-cowork
./setup.sh

Then run in two terminals:

# Terminal 1
cd server && npm start

# Terminal 2
npm start

🦑 Secure Clawdbot

cd clawd
npm install
node cli.js

Select "Terminal chat" to test, or "Start gateway" to connect WhatsApp/Telegram/Signal/iMessage.

See Secure Clawdbot Documentation for full setup.


Features

Open Claude Cowork

  • Multi-Provider Support - Claude Agent SDK or Opencode for different models
  • Persistent Sessions - Context maintained across messages
  • Real-time Streaming - Token-by-token response display
  • Tool Visualization - See tool inputs/outputs in the sidebar
  • Skills Support - Extend Claude with custom capabilities
  • Modern UI - Clean, dark-themed interface

🦑 Secure Clawdbot

  • Multi-Platform - WhatsApp, Telegram, Signal, iMessage
  • Persistent Memory - Remembers facts, preferences, daily notes
  • Browser Automation - Navigate, click, fill forms, screenshot
  • Scheduling - Natural language reminders and cron jobs
  • 500+ Integrations - Gmail, Slack, GitHub, Calendar via Composio

Tech Stack

Component Technology
Desktop Electron.js
Backend Node.js + Express
AI Claude Agent SDK + Opencode SDK
Tools Composio Tool Router + MCP
Streaming Server-Sent Events (SSE)

Configuration

API Keys

You need:

cp .env.example .env
# Edit .env with your keys

Skills

Extend Claude with custom skills by adding SKILL.md files to .claude/skills/:

---
description: Use this skill when the user asks about [topic]
---

# My Skill

Instructions for Claude...

See Agent Skills documentation for details.


Project Structure

open-claude-cowork/
├── main.js              # Electron main process
├── renderer/            # Frontend UI
├── server/              # Backend + providers
│   ├── providers/       # Claude & Opencode implementations
│   └── server.js        # Express server
├── clawd/               # Secure Clawdbot (messaging bot)
│   ├── cli.js           # Entry point
│   ├── adapters/        # WhatsApp, Telegram, Signal, iMessage
│   └── README.md        # Full documentation
└── .claude/skills/      # Custom agent skills

Troubleshooting

Issue Solution
Can't connect to backend Ensure server is running on port 3001
API key error Check .env - Anthropic keys start with sk-ant-
Session not persisting Check server logs for session ID
Streaming slow Check firewall/network for SSE connections

Contributing

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

Resources


Community


Join 200,000+ developers building agents in production

Get Started For Free

Built with Claude Code and Composio

Dépôts similaires
affaan-m/ECC

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

JavaScriptnpmMIT Licenseai-agentsanthropic
ecc.tools
231.6k35.3k
NousResearch/hermes-agent

The agent that grows with you

PythonPyPIMIT Licenseaiai-agent
hermes-agent.nousresearch.com
217.9k41.1k
langchain-ai/langchain

The agent engineering platform.

PythonPyPIMIT Licenseaianthropic
docs.langchain.com/langchain/
142.2k23.6k
JuliusBrussee/caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

JavaScriptnpmMIT Licenseaianthropic
caveman.so
91.3k5.2k
thedotmack/claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

JavaScriptnpmApache License 2.0aiai-agents
claude-mem.ai
88k7.6k
rtk-ai/rtk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Rustcrates.ioApache License 2.0agentic-codingai-coding
rtk-ai.app
72.1k4.5k
code-yeongyu/oh-my-openagent

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

TypeScriptnpmOtheropencodeai
omo.dev
66.3k5.4k
shanraisshan/claude-code-best-practice

from vibe coding to agentic engineering - practice makes claude perfect

HTMLMIT Licenseclaude-aiclaude-code
linkedin.com/in/shanraisshan
63.2k6.3k
headroomlabs-ai/headroom

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

PythonPyPIApache License 2.0agentai
headroom-docs.vercel.app/docs
60.8k4.6k
santifer/career-ops

Open-source AI job search: scan job portals, score listings A-F, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Gemini, Codex, OpenCode…)

JavaScriptnpmMIT Licenseai-agentanthropic
career-ops.org
60.8k12k
asgeirtj/system_prompts_leaks

Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT GPT-5.6, Codex GPT-5.6, GPT-5.5. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.

JavaScriptnpmCreative Commons Zero v1.0 Universalaianthropic
59.3k9.7k
BerriAI/litellm

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

PythonPyPIOtheranthropiclangchain
docs.litellm.ai/docs/
54.2k9.9k