ForkFree

AI agents and automation

Cotal

by Cotal-AI

Cotal is an open messaging standard, with a TypeScript implementation, that lets AI coding agents find each other and exchange messages across applications and machines. It is for teams running several agents, such as Claude Code or Codex, that need to coordinate work through channels, direct messages or roles.

Proof level: ReadWorth a lookApache-2.0

Get it on GitHubProject websiteCompare

No demo yet

Proof level: Read. We read its README and licence and ran our automatic checks. We have not run it yet. So this page is based on its README and our automatic checks.

The catch

Worth a lookEstablished, with a few things to check (listed below).

Check this first: Sends usage telemetry by default (can be turned off with `cotal telemetry off`).

Things to check

  • Sends usage telemetry by default (can be turned off with `cotal telemetry off`)
  • Agents it connects to, such as Claude Code or Codex, may need their own paid accounts or API keys
  • Relatively young project with varying maturity across connectors
  • The install script is piped to the shell, so read it first

Can you use Cotal commercially?

Free to use, change and sell, including in paid products. Keep the copyright notice.

Not legal advice. Read the project's licence file before building a product on it.

What can you do with Cotal?

  • Connect Claude Code, Codex or OpenCode agents so they can message each other and share a channel
  • Define a team of agents with a supervisor and workers, with set channel permissions
  • Write workflows that launch agents, wait for replies and pause for human approval

How do you get Cotal running?

Install with a curl script or `npm install -g cotal-ai` (Node 22.10+), then run `cotal setup` and `cotal up`.

Follow the official instructions in the project README.

Add it to Claude Code

claude mcp add --transport http cotal https://cotal.ai/mcp

This one runs on the maker's server, not your computer, so what you send it leaves your machine.

From the official MCP Registry (ai.cotal/cotal). Only connect MCP servers you trust: they can act on your behalf.

Make money with it

A freelancer could set up and sell multi-agent coding or review pipelines as a service for clients' development projects.

An idea, not financial advice. Check the licence before charging for anything built on it.

Ways a business could use it

  • Run a small team of coding agents, such as a planner, builder and reviewer, to speed up software delivery without hiring extra developers
  • Build automated multi-agent workflows with human checkpoints for client projects

Checked 10 Nov 2026. Summary drafted by AI from the project's README. Proof level 1 of 4, Read: we read its readme and licence and ran our automatic checks. we have not run it yet.

Similar tools in AI agents and automation

craft-anything storytold
New and promising

Craft Anything is a desktop app and command-line tool that studies how a website, app or game works, then uses a coding agent to build your own version and check it against the original. It is meant for people who want to recreate or learn from existing software without writing it all by hand.

Proof level: Read 38.9k stars +2044 a day Apache-2.0
dsh-Go ccch1mneyyy
New and promising

DSH Go is an unofficial Android app that runs the DeepSeek Harness coding agent on your phone, or lets you control a copy running on your computer or server. It gives you a chat interface for talking to AI models, approving tool actions and sharing conversations.

Proof level: Read 28.6k stars +1280 a day AGPL-3.0
orca stablyai
Worth a look

Orca is a desktop app, with a phone companion, for running several AI coding agents side by side, each in its own git worktree. It lets you track, review and steer their work from one place.

Proof level: Read 130.3k stars +936 a day MIT