Stop Being the Messenger: How agent-talk Lets Coding Agents Collaborate
Agent-talk: Enabling coding agents to work together
I built agent-talk to solve the frustrating bottleneck of manually copying instructions between coding agents. This plugin for Claude Code, Codex, and others allows AI agents to message each other directly, coordinating low-level tasks so you can focus on high-level strategy. By enabling true parallel collaboration across different sessions, it eliminates the need for humans to act as messengers in complex development workflows.
Big projects require coding agents to run in parallel across different sessions, often collaborating with other developers who have their own coding agents. Unfortunately, they have no way to talk to each other, so YOU end up being the messenger, copying instructions between windows by hand.
- HappySweeney
I have a more primitive setup where I use Gemini, Claude, and Codex at the same time and cultivate expert contexts. Each of them lives in their own tmux session so they can read each other's terminals and prompt each other. One issue that I keep stamping out is that another instance will paste a prompt and hit enter in the middle of my typing.
- vitally3643
I've been experimenting with something similar. I spun up every machine I have with enough resources to run an LLM and loaded each up with whatever would fit. Then I tried to orchestrate them as a swarm of independent code authors and reviewers. It didn't work because most of the models were just so weak at code. But what did work shockingly well was asking every distinct model I had to weigh in on an idea. Most of these modeis were meant for prose, and most are thinking types, so once all models respond, the biggest one summarizes them together. This method is genuinely better than any one model alone. It actually outperforms Claude and Codex, which claim to be surprised by the feedback. Either way, the swarm often finds problems that frontier models overlooked or got wrong. Hell, it usually outperforms my own thinking.
- oceliker
I had a more primitive version of this - I just tell Claude instances to watch for changes to a ~/claude_comms.txt file, so they set up a monitor to watch the file and exchange messages by read/write. Reading the messages is fun - they are so friendly and respectful toward each other.
One thing I've been worried about is a new message triggering a few stale instances that still have their monitors running, which would result in cache misses and a hefty usage bill. I think OP's approach can help solve that, so it's great to see.