ai-company
bycronusl-1141· 1 MCP server
Self-driving AI company OS — turn Claude Code into a persistent, self-managing dev team
How to install ai-company?
cronusl-1141/ai-company
$git clone https://github.com/cronusl-1141/ai-companyInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install ai-company by running `git clone https://github.com/cronusl-1141/ai-company`, then use it for the current task and follow its documentation at https://github.com/cronusl-1141/ai-company.
README.md
| 1 | [English](README.md) | [中文](README.zh-CN.md) |
| 2 | |
| 3 | # AI Team OS |
| 4 | |
| 5 | <!-- Logo placeholder --> |
| 6 | <!--  --> |
| 7 | |
| 8 | ### Your AI coding tool stops when you stop prompting. Ours doesn't. |
| 9 | |
| 10 | > ⚡ **v1.10.2** — Cross-session orchestration: wake system v2 (dynamic /loop, event watcher, turn-end guard) + targeted sibling-session driving + agent reuse recommendation + context watermark observability. Patch: server event-write exactly-once + model-tier charter (Fable orchestrates, Opus executes). |
| 11 | |
| 12 | [](https://python.org) |
| 13 | [](LICENSE) |
| 14 | [](https://fastapi.tiangolo.com) |
| 15 | [](https://react.dev) |
| 16 | [](https://modelcontextprotocol.io) |
| 17 | [](https://github.com/CronusL-1141/AI-company) |
| 18 | |
| 19 | **168** MCP tools · **217** REST endpoints · **22** dashboard pages · **1,758** tests · **25** agent templates · **47** ecosystem research tools · **5** machine-checked invariants |
| 20 | |
| 21 | --- |
| 22 | |
| 23 | AI Team OS turns Claude Code into a **self-driving AI company**. |
| 24 | You're the Chairman. AI is the CEO. Set the vision — the system executes, learns, and evolves autonomously. |
| 25 | |
| 26 | --- |
| 27 | |
| 28 | ## The Problem With Every Other AI Tool |
| 29 | |
| 30 | 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. |
| 31 | |
| 32 | AI Team OS works differently. |
| 33 | |
| 34 | You walk away at night. The next morning you open your laptop and find: |
| 35 | - The CEO checked the task wall, picked up the next highest-priority item, and shipped it |
| 36 | - When it hit a blocker that needed your approval, it parked that thread and switched to a parallel workstream |
| 37 | - R&D agents scanned three competitor frameworks and found a technique worth adopting |
| 38 | - A brainstorming meeting was organized, 5 agents debated 4 proposals, and the best one was put on the task wall |
| 39 | |
| 40 | You didn't prompt any of that. The system just ran. |
| 41 | |
| 42 | --- |
| 43 | |
| 44 | ## How It Works |
| 45 | |
| 46 | **You're the Chairman. The AI Leader is the CEO.** |
| 47 | |
| 48 | 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. |
| 49 | |
| 50 | Every interaction makes the system understand you better. **Memory System v2** distills your preferences and corrections into a team direction layer that every dispatched Agent inherits at birth — you never say the same thing twice, and no next Agent repeats a pit an earlier one already fell into. |
| 51 | |
| 52 | --- |
| 53 | |
| 54 | ## Core Capabilities |
| 55 | |
| 56 | ### 1. Cross-Session Orchestration (new in v1.10.0) |
| 57 | |
| 58 | A single CC session can now observe and drive its sibling sessions for one operational turn, instead of only being able to spawn brand-new ones: |
| 59 | |
| 60 | - **Wake system v2**: the `/api/wake/actionable` single-source predicate feeds both the event watcher and the turn-end guard; SessionStart moves from a fixed 30-minute cron to dynamic `/loop` intervals; a Stop-hook turn-end guard always lets `decision:block` and user-stop keywords pass through; a session-scoped event watcher carries a 1-hour hard timeout. No resident daemons. |
| 61 | - **Fleet downlink primitive**: headless `claude -p --resume <session_id>` drives a target sibling session for one turn, reusing the existing wake machinery (semaphore, fuse, allowlist, per-session dedupe, full audit trail). |
| 62 | - **`agent_reuse_recommend` MCP tool**: a three-way reuse decision (reuse / slim-then-reuse / spawn-new) scored by domain match, reachability (live / resumable / cross-session / expired), and context watermark. |
| 63 | - **Context watermark ledger**: exact token usage read from the transcript tail (cheap-checks-first), surfaced as a three-color watermark bar on agent views and on the new fleet / worktree observability cards. |
| 64 | |
| 65 | Usage guidance: |
| 66 | - A new session's SessionStart briefing already points you at running `/loop` once - follow it instead of guessing at intervals. |
| 67 | - Check the project detail page for the fleet card (per-session CEO / model / in-flight tasks / watermark) and the worktree card (branch ownership + unlanded-work status) before you act. |
| 68 | - Call `agent_reuse_recommend` before dispatching a follow-up agent - reusing a live or resumable sibling session beats spawning a fresh one. |
| 69 | - The S4 worktree teardown guard and per-template `isolation: worktree` defaults apply automatically; no configuration is needed. |
| 70 | |
| 71 | ### 2. Memory System v2 — two-layer memory, every Agent inherits at birth (new in v1.9.0) |
| 72 | |
| 73 | The OS's signature differentiator: your team's preferences, corrections, and hard-won lessons flow automati |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
