alook vs Auto-Company
Self-hosted collaboration layer that turns local coding agents (Claude Code, Codex, OpenCode) into an always-on "AI company" — per-agent email, org chart, kanban, shared memory. — versus — A fully autonomous 'AI company' on your own PC: 14 expert-modeled agents ideate, decide, code, deploy and market 24/7 — driven by Claude Code or Codex CLI, with a local dashboard.
Both stage an 'AI company' of local coding agents; alook is the collaboration layer you join (email, org charts), Auto-Company the hands-off experiment that runs the whole firm itself.
| alook | Auto-Company | |
|---|---|---|
| Stars | 944 | 1.3k |
| Forks | 144 | 166 |
| Language | TypeScript | Python |
| License | Apache-2.0 | — |
| Last activity | yesterday | 1 months ago |
| Topics | coding, orchestration | agents, orchestration |
| Curated connections | 9 | 2 |
alook — the curator's take
Pick alook when you already live in Claude Code or Codex and want those agents running as a persistent little team — email in and out, a kanban they work through, schedules, memory that compounds — without writing a line of orchestration code. It's a product, not a framework: BYO agent, you're the CEO. NOT for building agents programmatically (that's LangGraph/CrewAI territory), and if you need budgets, governance, and audit over a heterogeneous fleet, paperclip is the heavier, control-plane take on the same idea. Young project — expect sharp edges and a moving roadmap.
Auto-Company — the curator's take
The maximalist experiment: give 14 role-agents a company charter and let them run around the clock on your hardware. As a living demo of agentic workflows it's genuinely instructive — watch where autonomy compounds and where it wanders. Treat the 'without human intervention' framing as aspiration, NOT audit: unattended agents produce unattended mistakes at 24/7 speed, token bills to match, and there's NO license file at review time — check before building on it.