# AI Company > 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. - **Type:** MCP server - **Install:** `agentstack add mcp-cronusl-1141-ai-company` - **Verified:** Pending review - **Seller:** [CronusL-1141](https://agentstack.voostack.com/s/cronusl-1141) - **Installs:** 0 - **Category:** [Databases](https://agentstack.voostack.com/c/databases) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [CronusL-1141](https://github.com/CronusL-1141) - **Source:** https://github.com/CronusL-1141/AI-company ## Install ```sh agentstack add mcp-cronusl-1141-ai-company ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About [English](README.md) | [中文](README.zh-CN.md) # AI Team OS ### Your AI coding tool stops when you stop prompting. Ours doesn't. [](https://python.org) [](LICENSE) [](https://fastapi.tiangolo.com) [](https://react.dev) [](https://modelcontextprotocol.io) [](https://github.com/CronusL-1141/AI-company) --- 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. --- ## The Problem With Every Other AI Tool 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: - The CEO checked the task wall, picked up the next highest-priority item, and shipped it - When it hit a blocker that needed your approval, it parked that thread and switched to a parallel workstream - R&D agents scanned three competitor frameworks and found a technique worth adopting - A brainstorming meeting was organized, 5 agents debated 4 proposals, and the best one was put on the task wall You didn't prompt any of that. The system just ran. --- ## How It Works **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. --- ## Core Capabilities ### 1. Autonomous Operation The CEO never idles. It continuously advances work based on task wall priorities: - Checks the task wall for next highest-priority item when a task completes - When blocked on something requiring your approval, parks that thread and switches to parallel workstreams - Batches all strategic questions and reports them when you return — no interruptions for tactical decisions - Deadlock detection: if the loop stalls, it surfaces the blocker rather than spinning ### 2. Self-Improvement The system doesn't just execute — it evolves: - **R&D cycle**: Research agents scan competitors, new frameworks, and community tools. Findings go to brainstorming meetings where agents challenge each other. Conclusions become implementation plans on the task wall. - **Failure Alchemy**: Every failed task triggers root cause extraction, classification, and three outputs: - *Antibody* — failure stored in team memory to prevent the same mistake - *Vaccine* — high-frequency failure patterns converted into pre-task warnings - *Catalyst* — analysis injected into Agent system prompts to improve future execution ### 3. Team Collaboration Not a single Agent. A structured organization: - **25 professional Agent templates** (23 base + 2 debate roles) with recommendation engine — Engineering, Testing, Research, Management — ready out of the box - **8 structured meeting templates** with keyword-based auto-select, built on Six Thinking Hats, DACI, and Design Sprint methodologies - **Department grouping** — Engineering / QA / Research with cross-team coordination - Every meeting produces actionable conclusions. "We discussed but didn't decide" is not an outcome. ### 4. Full Transparency Nothing is a black box: - **Decision Cockpit**: event stream + decision timeline + intent inspection — every decision has a traceable record - **Activity Tracking**: real-time status of every Agent and what it's working on - **What-If Analyzer**: compare multiple approaches before committing, with path simulation and recommendations ### 5. Workflow Pipeline Orchestration Every task follows a structured, enforced workflow — no more ad-hoc execution: - **7 pipeline templates**: `feature` (Research→Design→Implement→Review→Test→Deploy), `bugfix`, `research`, `refactor`, `quick-fix`, `spike`, `hotfix` - **Auto-attach via `task_type`**: pass `task_type="feature"` to `task_create` and the pipeline mounts automatically - **Progressive enforcement**: hook detects tasks without pipelines — soft reminder → strong reminder → hard block (`exit 2`) on third occurrence - **Auto phase progression**: each stage recommends the right Agent template; `pipeline_advance` moves to next stage automatically - **Lightest escape hatch**: `quick-fix` (Implement→Test only) for truly trivial changes - **Channel communication**: `team:` / `project:` / `global` channels with `@mention` support - **Debate mode**: 4-round structured debate (Advocate→Critic→Response→Judge) via `debate_start` / `debate_code_review` - **Git automation**: `git_auto_commit` / `git_create_pr` / `git_status_check` for streamlined version control - **Semantic cache**: BM25 + Jaccard similarity matching with JSON persistence and TTL expiry - **Execution pattern memory**: success/failure pattern recording + BM25 retrieval + subagent context injection ### 6. Safety & Behavioral Enforcement Built-in guardrails so the system can run unsupervised without surprises: - **Guardrails L1**: 7 dangerous pattern detections + PII warnings + `InputGuardrailMiddleware` - **Local agent blocking**: all non-readonly agents must declare `team_name`/`name` — prevents rogue background agents - **S1 safety rules**: regex-based scan catches destructive commands (rm -rf, force push, hardcoded secrets) including uppercase flags and heredoc patterns - **4-layer defense rule system**: 48+ rules covering workflow, delegation, session, and safety layers - **File lock / workspace isolation**: acquire/release/check/list + TTL=300s + hook warnings to prevent concurrent edits - **Agent trust scoring**: trust_score (0-1) auto-adjusts on task success/failure, weighted into auto_assign - **Agent Watchdog heartbeat**: `agent_heartbeat` / `watchdog_check` with 5-min TTL — detects stalled or crashed agents automatically - **SRE error budget model**: GREEN/YELLOW/ORANGE/RED 4-level response with sliding window (20 tasks), `error_budget_status` / `error_budget_update` tools - **Completion verification**: `verify_completion` checks task status + memo existence — prevents hallucinated "done" reports - **Ecosystem integration recipes**: 4 preset recipes (GitHub / Slack / Linear / Full-stack team) via `ecosystem_recipes()` tool - **`find_skill` 3-layer progressive discovery**: quick recommend → category browse → full detail, reducing tool-call overhead ### 7. Zero Extra Cost Runs entirely within your existing Claude Code subscription: - No external API calls, no extra token spend - MCP tools, hooks, and Agent templates are all local - 100% utilization of your CC plan ### 8. Ecosystem Research Platform (progressive funnel in v1.5.0) 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: - **Stage 0 — Auto shallow-summary on archive**: newly-archived repos automatically get a 200-400 char `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. - **Stage 1 — On-demand architecture analysis**: user picks research direction ("memory_system") → batch-dispatch `backend-architect` agents to read architecture key files - **Stage 2 — Multi-perspective debate**: triggers existing `debate_start` (NOT a built-in debate engine — **reuses meeting system**). Meeting → ecosystem reverse-writeback hook reminds Leader to record verdicts back to deep_review - **Stage 3 — Reference / Integrate marking**: `mark_as_reference` adds tag for future quick recall (avoid re-deep-scanning); `start_integration` triggers existing `task_create` for actual implementation - **Project-customizable thresholds**: each project sets `min_stars` / `top_n` / `refresh_interval_days` / `focus_topics`. AI Team OS default: stars ≥ 5K, top 200, focus on claude-code / mcp / agent-framework - **Active vs Full dual-view**: data is **append-only forever**. Stars-falling repos kept (just `is_active=False`); stars climbing back auto-promotes + re-queues Stage 0 - **Dashboard `/ecosystem`**: list with stage badges + research timeline + project filter dropdown (view a project's ecosystem) + candidate-filter page (`/ecosystem/research`) + per-project settings tab - **30+ MCP tools / 15+ REST endpoints / SQLite append-only history snapshots** --- ## It Built Itself AI Team OS managed its own development: - Organized 5 innovation brainstorming meetings with multi-agent debate - Conducted competitive analysis across CrewAI, AutoGen, LangGraph, and Devin - Shipped 67 tasks across 5 major innovation features - Generated 14 design documents totaling 10,000+ lines The system that builds your projects... built itself. --- ## How It Compares | Dimension | AI Team OS | CrewAI | AutoGen | LangGraph | Devin | |-----------|-----------|--------|---------|-----------|-------| | **Category** | CC Enhancement OS | Standalone Framework | Standalone Framework | Workflow Engine | Standalone AI Engineer | | **Integration** | MCP Protocol into CC | Independent Python | Independent Python | Independent Python | SaaS Product | | **Autonomous Operation** | Continuous loop, never idles | Task-by-task | Task-by-task | Workflow-driven | Limited | | **Meeting System** | 8 structured templates with auto-select | None | Limited | None | None | | **Failure Learning** | Failure Alchemy (Antibody/Vaccine/Catalyst) | None | None | None | Limited | | **Decision Transparency** | Decision Cockpit + Timeline | None | Limited | Limited | Black box | | **Workflow Orchestration** | 7 pipeline templates + progressive enforcement | None | None | Manual | None | | **Rule System** | 4-layer defense (48+ rules) + behavioral enforcement | Limited | Limited | None | Limited | | **Agent Templates** | 25 ready-to-use + recommendation engine | Built-in roles | Built-in roles | None | None | | **Dashboard** | React 19 visualization | Commercial tier | None | None | Yes | | **Open Source** | MIT | Apache 2.0 | MIT | MIT | No | | **Claude Code Native** | Yes, deep integration | No | No | No | No | | **Extra Cost** | $0 (CC subscription only) | API costs | API costs | API costs | $500+/mo | --- ## Architecture ``` ┌─────────────────────────────────────────────────────────────────┐ │ User (Chairman) │ │ │ │ │ ▼ │ │ Leader (CEO) │ │ ┌────────────┼────────────┐ │ │ ▼ ▼ ▼ │ │ Agent Templates Task Wall Meeting System │ │ (25 roles) Loop Engine (8 templates) │ │ │ │ │ │ │ └────────────┼────────────┘ │ │ ▼ │ │ ┌──────────────────────┐ │ │ │ OS Enhancement Layer│ │ │ │ ┌──────────────┐ │ │ │ │ │ MCP Server │ │ │ │ │ │ (107 tools) │ │ │ │ │ └──────┬───────┘ │ │ │ │ │ │ │ │ │ ┌──────▼───────┐ │ │ │ │ │ FastAPI │ │ │ │ │ │ REST API │ │ │ │ │ └──────┬───────┘ │ │ │ │ │ │ │ │ │ ┌──────▼───────┐ │ │ │ │ │ Dashboard │ │ │ │ │ │ (React 19) │ │ │ │ │ └──────────────┘ │ │ │ └──────────────────────┘ │ │ │ │ │ ┌──────────▼──────────┐ │ │ │ Storage (SQLite) │ │ │ │ + Alembic Migration│ │ │ │ + Memory System │ │ │ └─────────────────────┘ │ └─────────────────────────────────────────────────────────────────┘ ``` ### Five-Layer Technical Architecture ``` Layer 5: Web Dashboard — React 19 + TypeScript + Shadcn UI (18 pages) Layer 4: CLI + REST API — Typer + FastAPI Layer 3: Team Orchestrator — LangGraph StateGraph Layer 2: Memory Manager — Mem0 / File fallback Layer 1: Storage — SQLite (development) / PostgreSQL (production) + Alembic migrations ``` ### Hook System (9 Lifecycle Events — The Bridge Between CC and OS) ``` SessionStart → session_bootstrap.py — Inject Leader briefing + 5 core rules + team state SessionEnd → send_event.py — Record session end event SubagentStart → inject_subagent_context.py — Inject sub-Agent OS rules (2-Action etc.) SubagentStop → send_event.py — Record sub-Agent lifecycle event PreToolUse → workflow_reminder.py — Workflow reminders + safety guardrails PostToolUse → send_event.py — Forward events to OS API UserPromptSubmit → context_monitor.py — Monitor context usage rate Stop → send_event.py — Record stop event PreCompact → pre_compact_save.py — Auto-save progress before context compression ``` --- ## Quick Install (AI-Assisted) Tell Claude Code: > "Read https://github.com/CronusL-1141/AI-company/blob/master/INSTALL.md and follow the instructions to install AI Team OS" Claude Code will read the install guide and walk you through the setup automatically. --- > **Important**: Install AI Team OS to your system Python, not inside a project virtual environment. > If installed in a venv, AI Team OS will only work in that specific project. > Run `deactivate` first if a venv is currently active, then install. --- ## Quick Start ### Prerequisites - Python >= 3.11 - [uv](https://docs.astral.sh/uv/getting-started/installation/) (`pip install uv`) - Claude Code (MCP support required) - Node.js >= 20 (Dashboard frontend, optional) ### Option A: Plugin Install (Recommended) ```bash # Install uv (Python package runner, required for MCP server) pip install uv # Add marketplace + install plugin claude plugin marketplace add CronusL-1141/AI-company claude plugin install ai-team-os # Restart Claude Code — first launch takes ~30s to set up dependencies # Subsequent launches are instant # Update to latest version anytime claude plugin update ai-team-os@ai-team-os ``` > **Note**: First launch after install takes ~30 seconds while dependencies are automatically configured. This only happens once — subsequent sessions start instantly with 107 MCP tools ready. ### Option B: Manual Install ```bash # Step 1: Clone the repository git clone https://github.com/CronusL-1141/AI-company.git cd AI-company # Step 2: Run the installer (auto-configures MCP + Hooks + Agent templat … ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [CronusL-1141](https://github.com/CronusL-1141) - **Source:** [CronusL-1141/AI-company](https://github.com/CronusL-1141/AI-company) - **License:** MIT Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** yes - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: flagged — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-cronusl-1141-ai-company - Seller: https://agentstack.voostack.com/s/cronusl-1141 - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.