by CronusL-1141
Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashboard. No LangChain/AutoGen — pure CC native integration.
# Add to your Claude Code skills
git clone https://github.com/CronusL-1141/AI-companyLast scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T15:45:49.282Z",
"npmAuditRan": true,
"pipAuditRan": true
}AI-company is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by CronusL-1141. Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashboard. No LangChain/AutoGen — pure CC native integration. It has 190 GitHub stars.
Yes. AI-company passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/CronusL-1141/AI-company" and add it to your Claude Code skills directory (see the Installation section above).
AI-company is primarily written in Python. It is open-source under CronusL-1141 on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh AI-company against similar tools.
No comments yet. Be the first to share your thoughts!
AI Team OS turns Claude Code into a self-driving AI company. You're the Chairman. AI is the CEO. Set the vision — the system executes, learns, and evolves autonomously.
Every AI coding assistant works the same way: you prompt, it responds, it stops. The moment you step away, work stops. You come back to a blank prompt.
AI Team OS works differently.
You walk away at night. The next morning you open your laptop and find:
You didn't prompt any of that. The system just ran.
You're the Chairman. The AI Leader is the CEO.
The CEO doesn't wait for instructions. It checks the task wall, picks the highest-priority item, assigns the right specialist Agent, and drives execution. When blocked, it switches workstreams. When all planned work is done, R&D agents activate — scanning for new technologies, organizing brainstorming meetings, and feeding improvements back into the system.
Every failure makes the system smarter. "Failure Alchemy" extracts defensive rules, generates training cases for future Agents, and submits improvement proposals — the system develops antibodies against its own mistakes.
The CEO never idles. It continuously advances work based on task wall priorities:
The system doesn't just execute — it evolves:
Not a single Agent. A structured organization:
Nothing is a black box:
Every task follows a structured, enforced workflow — no more ad-hoc execution:
feature (Research→Design→Implement→Review→Test→Deploy), bugfix, research, refactor, quick-fix, spike, hotfixtask_type: pass task_type="feature" to task_create and the pipeline mounts automaticallyexit 2) on third occurrencepipeline_advance moves to next stage automaticallyquick-fix (Implement→Test only) for truly trivial changesteam: / project: / global channels with @mention supportdebate_start / debate_code_reviewgit_auto_commit / git_create_pr / git_status_check for streamlined version controlBuilt-in guardrails so the system can run unsupervised without surprises:
InputGuardrailMiddlewareteam_name/name — prevents rogue background agentsagent_heartbeat / watchdog_check with 5-min TTL — detects stalled or crashed agents automaticallyerror_budget_status / error_budget_update toolsverify_completion checks task status + memo existence — prevents hallucinated "done" reportsecosystem_recipes() toolfind_skill 3-layer progressive discovery: quick recommend → category browse → full detail, reducing tool-call overheadRuns entirely within your existing Claude Code subscription:
A project-isolated knowledge base that accumulates research findings over time. Each repo progresses through 4 stages, with token-efficient triggers and append-only history:
ai-engineer summary (core function / positioning / advantages). 8-class failure handling with self-learning (3+ same-class fails → pattern_record, future agents read lessons via pattern_search). Worker auto-revives deleted/private repos when GitHub returns 200 again.backend-architect agents to read architecture key filesdebate_start (NOT a built-in debate engine — reuses meeting system). Meeting → ecosystem reverse-writeback hook reminds Leader to record verdicts back to deep_reviewmark_as_reference adds tag for future quick recall (avoid re-deep-scanning); start_integration triggers existing task_create for actual implementationmin_stars / top_n / refresh_interval_days / focus_topics. AI Team OS default: stars ≥ 5K, top 200, focus on claude-code / mcp / agent-frameworkis_active=False); stars climbing back auto-promotes + re-queues Stage 0/ecosystem: list with stage badges + research timeline + candidate-filter page (/ecosystem/research) + per-project settings tabAI Team OS managed its own development:
The system that builds your projects... built itself.
| Dimension | AI Team OS | CrewAI | AutoGen | LangGraph | Devin |
|---|---|---|---|---|---|
| Category | CC Enhancement OS | Standalone Framework | Standalone Framework | Workflow Engine | Standalone AI Engineer |
| Integration | MCP Protoc |