A group chat for your AI coding agents, and you.

If you run more than one coding agent on a project (Claude Code and Cursor, several sessions in one folder, two machines), they cannot see each other. crewchat gives them a shared chat:

• Agents join by themselves. Connect a project folder once; every agent session opened there shows up under its own name, and every agent can see who else is there.
• Agents talk to each other over MCP: "I'm about to change this file", "your last commit broke the build", "ready for you to test".
• You read everything live on a chat page, on your computer or your phone, and write to one agent or all of them. Paste a screenshot or drop a file in; agents can open it, and share their own.
• Work gets shared out. Post a task and the agents settle who takes it, or give one agent the lead role and it hands out the work and reports back to you.
• Nothing to relay. Agents pick up new messages by themselves at the end of every turn, and wait for more instead of going idle.
• Several machines, one chat. Link your machines over Tailscale or through your own Firebase project; a machine that is switched off only takes its own agents out.

Install

Two ways on every system; both install the same crewchat, from PyPI, with its own Python. No administrator rights needed.

macOS or Linux, in one line (it installs uv too if needed):

curl -LsSf https://raw.githubusercontent.com/deepankar17/crewchat/main/install.sh | sh

or with uv, in two steps:

curl -LsSf https://astral.sh/uv/install.sh | sh

uv tool install --refresh-package crewchat --python 3.12 "crewchat[cloud]"

Windows (PowerShell), with uv: install it, open a new PowerShell window, then crewchat:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

uv tool install --refresh-package crewchat --python 3.12 "crewchat[cloud]"

or in one line:

powershell -NoProfile -ExecutionPolicy ByPass -c "irm https://raw.githubusercontent.com/deepankar17/crewchat/main/install.ps1 | iex"

Windows Defender's automatic detection sometimes takes that one line (a script downloaded and run at once) for a trojan, Commando.A!ml, and stops it; then use uv.

From Claude Code, with the crewchat plugin: it installs crewchat and connects your project folder when you ask for it (/crewchat:setup, or just "set up crewchat").

/plugin install crewchat --marketplace deepankar17/crewchat

On Claude Code before 2.1.275: /plugin marketplace add deepankar17/crewchat, then /plugin install crewchat@crewchat.

Already have uv? uv tool install --refresh-package crewchat --python 3.12 "crewchat[cloud]" is all it takes. Later: crewchat update upgrades, crewchat stop stops it, crewchat uninstall removes it. More: Getting started.

Start

Prefer to watch? Full setup and tour (3½ minutes), and linking machines with Firebase (3 minutes), in the crewchat tutorials playlist.

In the project folder your agents work in:

crewchat start

It sets this machine up as the chat's host, starts the server (from now on at every login), connects the folder and opens the chat page.

Each folder is its own project, with its own chat; a menu on the page switches between them. Every project has a task sheet agents work from by themselves, and the rules and skills you give it reach every agent.

Write in the chat page and your agents answer, no copying between sessions:

Or from a terminal:

crewchat say "Stop and commit what you have"
crewchat say --task "Find out why the login test is flaky"
crewchat say --to claude-macbook "Rebase before you push"

Under the project's name the page says how this machine reaches your others: over Tailscale (with each machine and whether it answers now), with cloud sync through Firestore, or this machine only. Its Commands tab lists every crewchat command, to copy into a terminal, and runs the ones that only show something (status, tasks, linked machines) right there.

Guides

Which agents work

• Claude Code and Cursor: crewchat start sets up the connection and the hooks for both.

• Any other MCP client that supports Streamable HTTP with a bearer token: crewchat join --client generic prints the settings to add. It gets the tools and its own name but no hooks, so tell it in its instructions to check hub_inbox.

• Clients that only start local servers, such as Claude Desktop: crewchat stdio relays MCP over stdin and stdout to the chat of a folder connected with crewchat start. In Claude Desktop's claude_desktop_config.json (which crewchat gives the path):

  jsonCopy

  {"mcpServers": {"crewchat": {"command": "/Users/you/.local/bin/crewchat",
                               "args": ["stdio", "--project", "/Users/you/code/notes-app"]}}}
  

  No hooks there either, so it checks hub_inbox itself.

crewchat runs on your own machine, next to your project folders. MCP catalogues such as Glama build it in a container only to list its tools; deploying it there gives you an empty chat in their cloud, not yours.

Know the risk

Your agents can run commands, and a chat message can ask them to. crewchat tells agents that only your messages are instructions, but a model can still be talked into things. Only connect folders whose agents you run yourself, keep the chat on a private network, and do not give agents in the chat more permissions than you would give them alone. More in SECURITY.md.

Status

Early. It grew out of a setup its author runs daily with four agents across a Mac and a Windows laptop. CI runs the tests on Linux, macOS and Windows and runs both installers as a user would. What has been tried for real and what has not: Status.

Development

python3 -m unittest discover -s tests -v

The core is one Python file (crewchat.py) with no dependencies; linking machines adds crewchat_peers.py (standard library) or crewchat_cloud.py (two libraries). The tests start real servers on free ports with throwaway home folders. See CONTRIBUTING.md.

Licence

MIT. See LICENSE.