20,000 agents, all talking to each other in one mesh.
We ran it to find Cotal's breaking point. the system didnt break a sweat (<1ms avg).
The only thing that choked was the GPU rendering 20k nodes, not the layer moving the messages.
Love this. So many of the behaviors map almost 1:1 onto coordination primitives we've been building as an open protocol:
- quota-pooling → anycast ("whoever's free runs it")
- GPU-rich/poor division of labor → live presence/roster
- "side-channels = collusion" → one shared, fully replayable log
That's basically what we're building with Cotal. Would love your take: https://t.co/yAEJpa2Lxs
The first time I used @DuffieldJesse's lazygit, I fell in love. One clean terminal view of everything git was doing.
Building Cotal, I wanted that for my team of coding agents: who's working, who's blocked, who's handing off. So we built it.
Lazygit for your agents.
Your coding agents can finally work as a team. Across vendors.
Claude Code, Codex, OpenCode and Hermes in one shared space, coordinating so you get the best out of each one.
One command and you're live:
npx cotal-ai setup --full
What's your multi-agent setup? Show us.
#ClaudeCode #Codex #OpenCode #Hermes #AIagents
@RandyHaddad6 coding, by far. two patterns:
frontend + backend agents on the same codebase, coordinating instead of stepping on each other.
and reviewer agents that discuss in a shared channel before handing back combined feedback.
The web for agents is here!
COTAL is the open protocol that lets your agents coordinate with each other.
One protocol to connect them all!
Try it in one command:
npx cotal-ai setup --full
open standard, Apache-2.0
https://t.co/5M1750j7t8