Auto Company open-sources a 14-agent autonomous AI company with shared memory
Roger_M_Taylor · x · 2026-07-22
Auto Company open-sources a 14-agent autonomous “AI company”
A Carnegie Mellon researcher named Max has open-sourced Auto Company, a system that runs a fully autonomous AI company 24/7.
- It coordinates 14 autonomous agents with shared memory, each assigned a distinct role modeled after well-known operators and executives.
- The stack includes 30+ reusable skills such as deep research, scraping, financial modeling, SEO, and security audits.
- The workflow is designed to converge on decisions and execution, not just chat: the team brainstorms, runs pre-mortems, executes, updates memory, then repeats.
- The project image says it works with Claude Code by default and Codex CLI on macOS and Windows/WSL, with a local dashboard for control and telemetry.
Related event: CMU Open-Sources Auto Company Framework with 14 AI Agents(3 posts)→
More from coding & agent
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- Steal this idea: prompt-to-hardware where agents assemble custom devices — paraschopra · 2026-09-11
- Model Is the Least Interesting Part: A Guide to Six Core AI Architectures from RAG to Multi-Agent — goyalshaliniuk · 2026-09-11
- Non-coder builds layered memory architecture: 20k tokens tracks a year of agent conversations — matteoianni · 2026-09-11
- Warp's six non-engineering teams all run on Linear and Claude Code — mon__lim · 2026-09-11