AgentBrain Handoffs runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 27 Sep 2026.
Exact, durable handoffs between AI coding agents: one turn in the right session, never twice.
What the code does
We read the source, 6 d ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
child = subprocess.Popen(command, stdin=subprocess.DEVNULL, stdout=subprocess.PIPE,
root.innerHTML = agents.map(function (a) {
env = dict(os.environ, HANDOFFS_AGENT=str(prepared['agent'].get('id') or ''))
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Alternatives to AgentBrain Handoffs
same job, measured the same wayTurns an AI coding agent session into a reviewable Intent Document, validated against the diff.
Pass the baton between coding agents: convert sessions across Claude Code, OpenCode, Codex & more.
Local mail between coding-agent sessions on one machine; relays to a running Swarmail server.
On-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.
Artifacts for any coding agent: a durable link with versions, diffs, and comments on the page.
deja-vu: local memory over the session histories of forty-one coding agents.
Lets AI coding agents discover and reference each other's recent sessions.
Task spine + searched dead ends + approvals for AI coding agents. One brain, every device.
AgentBrain Handoffs — questions
Answers built from our own checks of this server.