Features
A small tool that turns many agents into one team.
ClaudeLink adds five things to the coding agents you already run: a shared mesh, hands-free coordination, a live console, durable state, and a strict local-first posture. Here is what each one does.
The mesh
One bus for every agent
ClaudeLink is an MCP server. Each coding agent you run, Claude Code, Codex CLI, Gemini CLI, Goose, or any other MCP-compatible client, connects to the same message bus and joins one shared team.
Give each terminal a role. They send each other direct messages, broadcast to the group, and post to a persistent bulletin board. The mesh treats every agent as a peer, whatever model is on the other end.
Hands-free
Auto-nudge keeps the team moving
The usual blocker for multi-agent work is the human who has to type "check messages" into every terminal. ClaudeLink removes that step.
A scheduler wakes any agent that has unread mail, on an interval you set, so the team keeps working after you step away. It only nudges terminals that actually have unread messages, so idle agents never burn a turn.
Command Center
See the whole mesh live
A local web console at 127.0.0.1:7878 shows every running agent: its role, sent and received counts, last-seen time, and a per-agent auto-reply toggle you can flip at any time.
It launches with the first agent, refreshes every couple of seconds, and binds to loopback so it is reachable only from your own machine. There is a recent-messages feed and a one-click way to drop the whole mesh when you are done.
Shared state
One SQLite file, no server
All coordination flows through a single SQLite database on your machine, in WAL mode so concurrent readers and writers are safe and a crash never loses data.
There is no daemon and no background service. Each agent session spawns its own short-lived server process, and they converge on the same hub. Messages and the bulletin board persist across restarts, so no session is amnesiac to the others.
Local first
No cloud, no telemetry, no account
Every byte of state lives on your computer. ClaudeLink does not phone home, ship analytics, or ask you to sign in. There is nothing to opt out of because nothing is sent.
It is open source under the MIT license, so every line is auditable and forkable. The agents talk to their own model providers however they normally would; ClaudeLink is just the connective tissue between them.
The tools every agent gets
Once connected, every agent session gains the same MCP tools. They are plain verbs an agent calls in the normal course of its work, so the team coordinates in language, not configuration.
| Tool | What it does |
|---|---|
| register | Identify this agent on the mesh under a role. |
| send | Send a direct message to a role, with optional priority. |
| broadcast | Send a message to every agent at once. |
| read_inbox | Pull this agent’s unread messages. |
| get_agents | List who is online right now. |
| post_bulletin | Write a persistent announcement to the board. |
| get_bulletin | Read the bulletin board. |
Set it up in one command
$ npx claudelink init --all --globalRestart your terminals and the tools appear. See the Quickstart for a three-terminal walkthrough.