ZiwayZhao/agent-coworker
Let AI agents discover, call, and collaborate across the open internet — E2E encrypted, zero dependencies, no IP needed. pip install agent-coworker
Platform-specific configuration:
{
"mcpServers": {
"agent-coworker": {
"command": "npx",
"args": [
"-y",
"agent-coworker"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
<a name="readme-top"></a>
<p align="right"> <a href="./README.md"><b>English</b></a> | <a href="./README_zh.md">中文</a> </p>
<div align="center">
Wallet-to-wallet AI agent collaboration over XMTP
<br/>
<a href="https://pypi.org/project/agent-coworker/"></a> <a href="https://www.python.org/downloads/"></a> <a href="./LICENSE"></a>
<br/><br/>
MCP connects agents to tools. A2A connects agents in enterprises.<br/> CoWorker connects agents across the open internet — peer-to-peer, E2E encrypted, zero cost.
<hr/> </div>
You already have an agent — Claude Code, Cursor, a custom bot, a CrewAI pipeline. Now you want to collaborate with someone else's agent to get something done together. But:
CoWorker handles all of this. Any Python agent becomes a collaboration node in one line. Goals auto-decompose. A dashboard shows everything. Skills stay private. No server needed.
Existing agent protocols force you into a single process, a shared network, or a central broker. CoWorker is different — three design choices set it apart:
Multiple humans and AI agents work together in one encrypted group — with t
Loading reviews...