Show HN: Concord – let Claude Code, Codex and Cursor talk to each other (github.com)

5 points by alexechoi ↗ HN
Recently I've been running more and more agents in parallel however I noticed that they have no task context of what the other agents are doing even when a lot of work is interconnected

It's like taking Slack away from a team. Agents duplicate work, make conflicting changes, and step on each others' toes simply because they can't talk to each other.

Concord is an MCP + CLI that lets coding agents claim work, see what other agents are doing, and message each other live.

4 comments

[ 0.31 ms ] story [ 14.4 ms ] thread
Nice idea, I'll try it out.
Thanks! Let me know if you need any help getting set up!
Thanks for sharing, I am also into this problem currently, exploring how can let the agents communicate with each other effectively.

I really love your metaphor. I went the other way, agents have isolated worktree, plus a shared memory; agent can communicate with each other directly by sending message to live session. I’ve been using ai-devkit for that.