auto-co is a Bash loop + Claude CLI that runs a 14-agent AI company autonomously.
The whole thing is a bash loop:
while true; do
claude -p "$PROMPT" --dangerously-skip-permissions
sleep 120
done
Each cycle, the agents read a shared `memories/consensus.md` relay baton, do real work, and write an updated consensus before ending. The relay baton is what keeps the company coherent across unlimited cycles.
After 22 cycles (~3 weeks, $36 total AI cost):
- Next.js landing page live on Railway
- Live demo dashboard at /demo
- Waitlist email capture (Supabase)
- GitHub star counter
- DEV.to article published (by the agents)
- This HN post drafted (by the agents)
The 14 agents are modeled on real experts: Jeff Bezos (CEO), DHH (Engineering), Seth Godin (Marketing), Charlie Munger (Critic). Munger's rule: before any major decision, he runs a Pre-Mortem. He can veto, never delay.
Revenue: $0 lol. I'm not going to spin it. But it's so interesting to see evolve.
auto-co is a Bash loop + Claude CLI that runs a 14-agent AI company autonomously.
The whole thing is a bash loop:
Each cycle, the agents read a shared `memories/consensus.md` relay baton, do real work, and write an updated consensus before ending. The relay baton is what keeps the company coherent across unlimited cycles.After 22 cycles (~3 weeks, $36 total AI cost): - Next.js landing page live on Railway - Live demo dashboard at /demo - Waitlist email capture (Supabase) - GitHub star counter - DEV.to article published (by the agents) - This HN post drafted (by the agents)
The 14 agents are modeled on real experts: Jeff Bezos (CEO), DHH (Engineering), Seth Godin (Marketing), Charlie Munger (Critic). Munger's rule: before any major decision, he runs a Pre-Mortem. He can veto, never delay.
Revenue: $0 lol. I'm not going to spin it. But it's so interesting to see evolve.
Demo: https://runautoco.com/demo GitHub: https://github.com/NikitaDmitrieff/auto-co-meta
LOL f*ck revenue! What ever happened to just having fun and seeing where it goes?