Deploy Now

SaaS Alternative

Devin Factory AI Sweep AI

Categories

Developer Tools DevOps Automation AI Agents AI Development Multi-Agent System Autonomous Systems

Stars

2,720

Forks

436

Watchers

13

Developer links

Last Updated: 09-01-2026
Share on X

Auto Company

With over 2,700 GitHub stars, Auto Company is the first open-source framework that runs a fully autonomous AI company 24/7 — 14 specialized agents modeled after Jeff Bezos (CEO strategy), Werner Vogels (CTO architecture), Charlie Munger (critical analysis), DHH (full-stack engineering), Kelsey Hightower (DevOps), Seth Godin (marketing), and eight more domain experts collaborate through dynamic squad formation to ideate products, write code, deploy infrastructure, and execute marketing campaigns without human intervention. The five-layer architecture separates execution, orchestration, cognition, workflow routing, and observability, while the consensus memory pattern uses a single markdown file as a relay baton between cycles — no vector databases, no Redis, no embeddings required. A bash loop invokes Claude Code or OpenAI Codex CLI every 30 seconds, each cycle selecting 2-5 agents from the 14-person pool based on task context. Over 30 reusable skills handle specialized tasks from frontend design to competitive analysis and deployment automation. Circuit breakers trigger cooldown after consecutive errors, rate-limit detection auto-sleeps on API throttling, and sandbox rollback protects against destructive changes. The Python-powered web dashboard displays real-time cycle status, cost tracking per cycle averaging under $2, and agent activity visualization, with CLI control via make start, stop, monitor, pause, and resume. Supports macOS via launchd, Windows via WSL with systemd, and native Linux deployment. The npx create-auto-co command scaffolds a new AI company in seconds. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Auto Company

Benefits

  • Autonomous 24/7 Software Production
  • Fourteen specialized AI agents work continuously through daemon-managed cycles, ideating products, writing code, deploying services, and executing marketing — delivering real artifacts like landing pages and APIs without human intervention.
  • Expert-Level Decision Making
  • Each agent injects mental models from industry leaders — Bezos's Working Backwards methodology, Munger's inversion checklists, DHH's Majestic Monolith philosophy — producing decisions with genuine business and engineering depth.
  • Zero-Infrastructure State Management
  • The relay baton consensus pattern compresses entire company state into a single markdown file read and rewritten each cycle, eliminating vector databases, Redis, and embedding infrastructure entirely.
  • Built-In Resilience and Safety
  • Circuit breakers trigger cooldown after consecutive failures, rate-limit detection auto-sleeps on API throttling, sandbox rollback reverts destructive changes, and configurable guardrails in CLAUDE.md prevent unauthorized actions.

Features

  • Dynamic Squad Formation
  • Each cycle dynamically selects 2-5 optimal agents from the 14-person pool based on the current task, keeping costs under $2 per cycle on average.
  • Real-Time Web Dashboard
  • Python-powered local dashboard visualizes cycle status, cost consumption, agent activity, and decision history with full CLI control via make commands.
  • Dual Engine Support
  • Run with Anthropic Claude Code CLI or OpenAI Codex CLI, configurable per session via environment variables with optional model override support.
  • Cross-Platform Daemon Management
  • Native daemon support via launchd on macOS, systemd on Linux and WSL, with auto-start, auto-restart, pause, and resume controls built in.
  • Consensus Memory System
  • Single markdown relay baton pattern coordinates state across cycles without vector databases, Redis, or embeddings — fitting entirely within the LLM context window.
  • 30+ Reusable Skills
  • Modular skill definitions in .claude/skills/ handle specialized tasks from frontend design to competitive analysis, extensible by adding new markdown files.