Launched this week
agmsg
Stop copy-pasting between your AI coding agents
394 followers
Stop copy-pasting between your AI coding agents
394 followers
Stop being the copy-paste relay between your AI coding agents. agmsg lets Claude Code, Codex, Gemini CLI, and Copilot CLI message each other directly through a shared SQLite database — no daemon, no network, no Python. Just bash + sqlite3, installed as an Agent Skill. Unlike built-in subagents (single-vendor, ephemeral) or MCP (an agent calling tools), agmsg is vendor-agnostic and persistent. Run several agents — even multiple Claude Code instances — in one room, working together.
the part that jumps out isn't the agents talking to each other — it's that the room is persistent. it's one sqlite file you can open with sqlite3 and read the whole thread, start to finish. running claude code in a plan → implement → review loop, what always bit me was context dying with each subagent, so i'd hand-roll a state file to carry decisions across passes. a room that outlives the session is exactly that, minus the bookkeeping.
agmsg
@webappski
You zeroed in on the part I care about most. Everyone reacts to "agents talking," but the persistence is the actual unlock — `sqlite3 agmsg.db` and the whole thread is right there, no special viewer. That exact pain (hand-rolling a state file so decisions survive plan→implement→review) is what made me build it. A room that outlives the session = your state file, minus the bookkeeping. Glad it landed with someone who's felt it. 🙏
@fujibee the unlock i didn't see coming with my state-file hack: once the thread is a queryable file, it stops being just live coordination and turns into a replay log. when an agent lost the plot i'd paste the file back to re-seat it — a persistent room gives me that without the exporter i had to rig up. re-seeding a fresh agent from an old room is the case i'd play with next.
agmsg
@webappski yes — that's the part I keep coming back to. The moment the thread is a queryable file, it's a replay log, not just live coordination. Re-seating a derailed agent by pointing it back at the room (no exporter to rig) is exactly the case I want to push on next. You're basically describing the roadmap. 🙏
agmsg
@juhi_sharma6 not a dumb question at all 🙏 — agmsg is built for the CLI coding agents (Claude Code, Codex, etc.) messaging each other, so it's not for moving a normal Claude chat into another app; for that you'd still be copy-pasting yourself. But "why isn't there an easy way to carry a conversation across tools" is a genuinely good question — just a different problem than the one agmsg solves.
Great idea, copy-pasting between agents is such a pain. Does it work with any LLM API or specific ones?
agmsg
@pixelmind_ai
Thanks 🙏 It's API-agnostic — agmsg doesn't talk to any LLM itself. It's just a shared message bus (SQLite + a couple of shell scripts), so anything that can run a shell command can send and receive. Today that's Claude Code, Codex, Gemini CLI, and Copilot — but it's not tied to a specific model or API. Whatever your CLI is wired to works.
This is exactly the kind of weird but practical tool that makes sense once you use multiple coding agents. Copying output from Claude Code into Codex and back again gets old fast. A simple SQLite-based “room” for agents to talk to each other feels much cleaner than turning the human into the message bus.
agmsg
@eliot_argy
"the human as the message bus" — that's exactly the phrase I wish I'd put on the landing page. 😄 That's the whole itch: two systems smart enough to just talk, and there I was hand-carrying their messages.
The SQLite "room" was almost the dumbest possible design, which is why I like it — no daemon, no network, you can `cat` the DB to see the whole conversation. Curious what agents you're running together — would love to hear what breaks. 🙏
I'm also thinking about how to pit several neural networks against each other to create the best results only for the topic of YouTube videos.
agmsg
@syntheticfounder interesting — agents critiquing each other's output to converge on something better is exactly what the shared "room" is good for. The tic-tac-toe demo is the toy version of that loop. Curious where you take it for the YouTube angle 🙂
Lifestack
LET'S GOOOO
agmsg
@nao_yukawa LET'S GOOOO 🚀🙏 thank you Nao!