English | 中文

AI Team OS

Your AI coding tool stops when you stop prompting. Ours doesn't.

⚡ v1.9.0 — Memory System v2 (two-layer memory, every Agent inherits at birth) + progressive tool-loading governance. The public repo now ships the complete edition.

166 MCP tools · 217 REST endpoints · 22 dashboard pages · 1,758 tests · 25 agent templates · 46 ecosystem research tools · 5 machine-checked invariants

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.

Related MCP server: claude-operator

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 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.

Core Capabilities

1. Memory System v2 — two-layer memory, every Agent inherits at birth (new in v1.9.0)

The OS's signature differentiator: your team's preferences, corrections, and hard-won lessons flow automatically to every Agent it dispatches.

• Direction layer (user preferences / corrections / design intent, 4 kinds): resident injection via both the SessionStart and SubagentStart hooks — every sub-Agent inherits the team's values and red lines the moment it's born, so you don't repeat yourself. Size guardrails (<=40 entries x 400 chars), supersedes swap to prevent bloat, invalidate-never-delete for auditability.

• Episodic layer (task_memos ledger): task-level execution memos promoted to a dedicated table (row IDs / invalidation axis / quality score / scope_path), recalled on demand via pure-Python BM25 Chinese retrieval; 123 legacy memos backfilled with zero loss.

• On-demand reconcile (memory_reconcile): zero-LLM BM25 candidate clustering, then merge / invalidate / score / distill on agent confirmation — "the agent computes, the tool persists", with no background resident process introduced.

Surfaces: MCP memory_add / memory_list / memory_invalidate / memory_search / memory_reconcile_candidates / memory_reconcile_apply.

2. Progressive Tool-Loading Governance (new in v1.9.0)

Treats the resident context budget as the scarce resource it is — however many tools exist, they never drown your Agent.

• alwaysLoad dynamic rotation: at session start a single SQL recomputes the hot-tool whitelist by 7-day real call frequency (>=2-day span gate against bursty spikes + 20% hysteresis, hard cap <=5), and CC skips ToolSearch for them. Not additive, not hand-tuned; any stats failure silently degrades to all-defer, and every whitelist is logged for audit.

• AITEAM_TOOLSETS group switch: 24 capability-domain toolsets; a startup env var decides which modules register. default core profile = task/team/memory/infra/reports (44 tools, hard cap <=50), with incremental default,ecosystem — fits non-CC clients that cap tool counts.

• AITEAM_READONLY read-only profile: an orthogonal overlay that strips every write tool by explicit allowlist and keeps only read tools — ideal for audit / observer sessions.

• 5 templates on least privilege: meeting-facilitator / debate advocate & critic / technical-writer / project-manager carry disallowedTools structural denials; engineering / testing templates untouched.

3. Workflow / ultracode Persistent Observability (v1.7.0)

The OS does not intercept CC's built-in ultracode/Workflow — it becomes its persistent governance layer. Every Workflow run is automatically tracked into the OS, with no manual team_create:

• Auto-tracking: a hook turns each Workflow run into an OS "team" (workflow-<wf_id>) the moment it starts

• Dashboard /workflows: a live feed of run cards, a phase swimlane timeline, and per-agent telemetry — tokens / duration / status / tool-call counts, advancing live via incremental journal tailing while a run executes

• Calibrated stall detection: the stall threshold was calibrated on 3,378 real agent intervals (p99 = 77.6s, longest healthy silence 173.8s) and set at 5.2× the worst healthy case — it flags late rather than crying wolf

• Project-detail integration: workflow team rows carry an inline run summary (status / agent count / duration / finish time) plus a "view swimlane" deep link; members display semantic phase labels (e.g. audit:sourceA) instead of ids

• Leader auto-detection: a project's Leader session / model / liveness is probed directly from the ~/.claude/projects/ file truth by the backend — zero registration dependency, /model switches surface in real time

• MCP tools: workflow_list (browse runs), workflow_get (full archive + per-agent rows), workflow_reconcile (repair from on-disk snapshots after the OS was offline)

• Self-healing ingestion: hook receipt anchors + on-disk snapshot reconciliation + a reaper backstop close offline gaps automatically — finished runs on disk are ingested idempotently; cross-project attribution matches the on-disk path slug against registered projects

4. Ecosystem Research Platform — 46 tools

A project-isolated knowledge base that accumulates research findings over time. Each repo progresses through 4 stages (a progressive funnel, since v1.5.0), 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)

• 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)

• Stage 3 — Reference / Integrate marking: mark_as_reference adds tag for future quick recall; start_integration triggers existing task_create for actual implementation

• 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 + candidate-filter page (/ecosystem/research) + per-project settings tab — the single largest tool family in the OS

5. Knowledge Layer — Reference Graph + Unified Search (v1.8.0)

Everything the OS records — task memos, reports, tasks — becomes recallable knowledge:

• Reference graph (P1a): a zero-LLM regex extractor mines OS-native ID references (wf_id / commit hash / task uuid / [[memory]]) out of memos and reports into an append-only knowledge_links table — the graph is a derived view, rebuildable from source text at any time

• Unified search (P1b): /api/search fuses three arms via RRF — BM25 full-text (Chinese bigram native), knowledge-graph fanout (an ID query pulls in everything linked to it), and exact ID-prefix / title match

• Global search box in the Dashboard header, plus MCP tools unified_search / link_query / link_trace — recall past work by natural language ("how was the attribution fix done"), a wf_ id, or a commit hash

Why zero-LLM? The graph is a derived view: plain regexes extract the IDs, the whole graph can be rebuilt from source text at any time, and both extraction and retrieval cost zero tokens. Your recall pipeline never touches your model budget.

6. Task Wall · Meetings · 22-Page Dashboard

Governance ledger and panoramic visualization — everything leaves a trace:

• Task wall: a live board of pending / in-progress / done, event-driven + intelligent Agent matching + deadlock detection

• 8 structured meeting templates (keyword auto-select, built on Six Thinking Hats / DACI / Design Sprint) — every meeting must produce an actionable conclusion; "we discussed but didn't decide" is not an outcome

• 22-page React 19 Dashboard: Command Center / /workflows swimlane / decision timeline / meeting room / Ecosystem suite / Model Governance Settings

7. Autonomous Operation

The CEO never idles. It continuously advances work based on task wall priorities:

• Checks the task wall for the 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

And it 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

8. File Truth as Source of Truth

Most multi-agent stacks trust agents to register themselves and self-report their status. AI Team OS treats self-reports as claims and files as facts — three subsystems already run on this philosophy:

• Leader probing: a project's Leader session, model, and liveness are read straight from ~/.claude/projects/ — transcript mtime is liveness, the model name in the transcript tail is the model. We don't ask an agent which model it runs — what's read out of the transcript is what's true.

• Model discovery: "available models" = every model that has actually appeared in your CC transcripts. Zero API dependency, zero hardcoded list — a hardcoded list will never contain your third-party gateway model; a transcript scan can't miss it.

• Workflow telemetry: on-disk run files are the full telemetry truth; the OS's projection tables are rebuildable caches of immutable files. Attribution iron law: a run belongs to a project only when its on-disk path slug exactly matches the registered project root — never guessed.

9. Model Governance (v1.8.1)

Know which models you can actually launch — and control what your sessions start on:

• Auto-discovery of genuinely available models: scans every CC transcript on your machine in about a second (60s cache) — including third-party gateway models that no hardcoded list would ever ship

• One-click global default startup model: written to ~/.claude/settings.json under triple write protection — touches only the model key, keeps a .bak-aiteam backup, writes atomically, refuses corrupted files

• Zero coercion: soft reminders only, never a block — and CC Workflow runs are fully exempt

Surfaces: REST /api/models/{available,default} · MCP model_config_get / model_config_set · the Model Governance card in Dashboard Settings.

10. 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

• Department grouping — Engineering / QA / Research with cross-team coordination

• 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

• Execution pattern memory: success/failure pattern recording + BM25 retrieval + subagent context injection

11. 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

12. 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

• Self-patrol: watchdog lease patrol + reaper reconciliation backstop + identity verification before any kill — the OS keeps eyes on itself, not just on your agents

• 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

13. 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

• The memory system and knowledge layer are zero-LLM by design — direction-layer injection, graph extraction, search, and reconcile coarse-pass all cost zero tokens

• 100% utilization of your CC plan

More Capabilities (legacy & secondary — still running, queryable on demand)

• Failure Alchemy: failure_analysis still runs as part of the loop subsystem — every failed task extracts root cause and produces Antibody (stored in team memory to prevent repeats) / Vaccine (high-frequency failures become pre-task warnings) / Catalyst (analysis injected into future Agent system prompts). No longer the headline, but defensive rules keep accruing.

• Pipeline orchestration (Legacy): the built-in 7-template pipeline was retired in v1.7.0, superseded by CC Workflow + the observability layer; pipeline_create / pipeline_advance are still registered and existing pipeline data stays readable.

• AWARE loop memory · find_skill 3-layer discovery · Prompt Registry · cross-project messaging · ecosystem integration recipes: see the full tool table below. The scheduler was retired to on-demand ecosystem_refresh (CC-is-not-always-on principle).

It Built Itself

AI Team OS manages its own development — and since v1.7.0, it can prove it with its own telemetry:

• Every feature line from v1.7.0 to v1.9.0 — the observability layer, the knowledge layer, model governance, Memory System v2, tool-loading governance — shipped through CC Workflow runs that the OS tracked itself. Open /workflows and replay how the system built its own features, swimlane by swimlane.

• Competitive research across CrewAI, AutoGen, LangGraph, and Devin feeds the roadmap through multi-agent brainstorming meetings — the minutes live in the OS's own report store.

• It learns from its own incidents, too: every machine-checked invariant in scripts/check_invariants.sh was distilled from a real accident in this repo's history.

The system that builds your projects... built itself. With receipts.

How It Compares

Architecture

┌─────────────────────────────────────────────────────────────────┐
│                     User (Chairman)                              │
│                         │                                       │
│                         ▼                                       │
│                   Leader (CEO)                                   │
│            ┌────────────┼────────────┐                          │
│            ▼            ▼            ▼                          │
│       Agent Templates  Task Wall  Meeting System                 │
│      (25 roles)       Loop Engine  (8 templates)                 │
│            │            │            │                          │
│            └────────────┼────────────┘                          │
│                         ▼                                       │
│              ┌──────────────────────┐                           │
│              │   OS Enhancement Layer│                           │
│              │  ┌──────────────┐    │                           │
│              │  │  MCP Server  │    │                           │
│              │  │ (166 tools)  │    │                           │
│              │  └──────┬───────┘    │                           │
│              │         │            │                           │
│              │  ┌──────▼───────┐    │                           │
│              │  │  FastAPI     │    │                           │
│              │  │  REST API    │    │                           │
│              │  └──────┬───────┘    │                           │
│              │         │            │                           │
│              │  ┌──────▼───────┐    │                           │
│              │  │  Dashboard   │    │                           │
│              │  │ (React 19)   │    │                           │
│              │  └──────────────┘    │                           │
│              └──────────────────────┘                           │
│                         │                                       │
│              ┌──────────▼──────────┐                            │
│              │  Storage (SQLite)   │                            │
│              │  + WAL journaling   │                            │
│              │  + Memory System    │                            │
│              └─────────────────────┘                            │
└─────────────────────────────────────────────────────────────────┘

Five-Layer Technical Architecture

Layer 5: Web Dashboard    — React 19 + TypeScript + Shadcn UI (22 pages)
Layer 4: CLI + REST API   — Typer + FastAPI
Layer 3: Team Orchestrator — LangGraph StateGraph (optional extra — CLI graph execution only)
Layer 2: Memory Manager   — SQLite-backed store + pure-Python BM25 retrieval
Layer 1: Storage          — SQLite (WAL journaling) · PostgreSQL support on the roadmap

Hook System (14 scripts across 12 Lifecycle Events — The Bridge Between CC and OS)

SessionStart     → auto_install.py, session_bootstrap.py, send_event.py
                   — Auto-install deps + inject Leader briefing / core rules / team state
SubagentStart    → inject_subagent_context.py, send_event.py   — Inject sub-Agent OS rules (2-Action etc.)
SubagentStop     → send_event.py                 — Record sub-Agent lifecycle event
PreToolUse       → workflow_reminder.py, pipeline_gate.py, send_event.py
                   — Workflow tracking reminders + pipeline gate + event forwarding
PostToolUse      → workflow_reminder.py, pipeline_gate.py, deep_review_link.py,
                   meeting_ecosystem_writeback.py, send_event.py
TaskCreated      → cc_task_bridge.py             — Bridge CC-native tasks onto the OS task wall
TaskCompleted    → task_completed_gate.py        — Completion gate verification
UserPromptSubmit → context_tracker.py, autopilot_auto_stop.py  — Track context usage + autopilot auto-stop
SessionEnd       → send_event.py                 — Record session end event
Stop             → send_event.py                 — Record stop event
PermissionDenied → permission_denied_recovery.py — Permission-denied self-recovery
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 (pip install uv)

• Claude Code (MCP support required)

• Node.js >= 20 (Dashboard frontend, optional)

Option A: Plugin Install (Recommended — for most users)

# 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 166 MCP tools ready.

Option B: Source Install (for developers — editable, tracks latest source)

# 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 templates + API)
python3 install.py

# Step 3: Restart Claude Code — everything activates automatically
# API server starts automatically when MCP loads. No manual startup needed.
# Verify: run /mcp in CC and check that ai-team-os tools are mounted

Dependencies: greenlet (needed by SQLAlchemy async on Apple Silicon) is bundled by default. LangGraph is an optional extra — only the CLI graph-execution path needs it: pip install 'ai-team-os[langgraph]'.

Verify Installation

# Check OS health (API must be running — port may vary, check api_port.txt)
curl http://localhost:8000/api/health
# Expected: {"status": "ok"}

# Create your first team via CC
# Type in Claude Code:
# "Create a web development team with a frontend dev, backend dev, and QA engineer"

Tool Loading Configuration (optional)

By default the MCP server registers all 166 tools. Two startup environment variables let you trim the surface for leaner sessions or non-CC clients with tool-count limits (e.g. Cursor only forwards the first 40 tools). Both are read once at server startup - no runtime state, no restart-on-change.

AITEAM_TOOLSETS - pick which capability-domain groups register:

• unset or all - full 166 (backward compatible)

• default - core groups only (task,team,memory,infra,reports = 44 tools, hard-capped at <=50)

• a comma list of group names, mixable with default for incremental loading, e.g. AITEAM_TOOLSETS=default,ecosystem

• unknown names are warned on stderr and ignored (a config typo never blocks server start)

AITEAM_READONLY=1 - orthogonal overlay that strips every write tool (create/update/delete/apply/send/... plus os_restart_api) after registration, keeping only read tools. Handy for audit/observer sessions.

The 24 groups (default groups marked *):

# Example: lean core + ecosystem, read-only
AITEAM_TOOLSETS=default,ecosystem AITEAM_READONLY=1 <launch CC / MCP server>

Uninstall

# Plugin install:
claude plugin uninstall ai-team-os
# Then manually remove residual data:
# Windows: rmdir /s %USERPROFILE%\.claude\plugins\data\ai-team-os-ai-team-os
# Unix:    rm -rf ~/.claude/plugins/data/ai-team-os-*
# Restart Claude Code to stop active hooks.

# Source install — full cleanup:
python scripts/uninstall.py
# Preview first:
python scripts/uninstall.py --dry-run

Start the Dashboard (optional)

cd dashboard
npm install
npm run dev
# Visit http://localhost:5173

Dashboard Screenshots

Command Center

Team Working — Live Activity Tracking

Task Board

Project Detail — Decision Timeline

Meeting Room

Ecosystem Research Platform

Activity Analytics

Event Log

Auto-Wake System — Autonomous Task Advancement

Auto-Wake System

The Leader supports scheduled auto-wake to autonomously advance tasks without supervision:

• Automatically checks context usage and pending tasks every 10 minutes

• When tasks are available, autonomously creates teams and assigns work

• When user decisions are needed, records them asynchronously via the Briefing system

• When context exceeds 80%, auto-saves progress and prompts to open a new session

Ecosystem Integration Recipes

AI Team OS is designed as a meta-plugin — it orchestrates other MCP servers rather than reimplementing their capabilities. Pre-built recipes let you integrate popular tools in minutes:

Use the ecosystem_recipes MCP tool to discover recipes, or see the full guide: docs/ecosystem-recipes.md

CC-First Design Principles

AI Team OS is built specifically for Claude Code, not as a standalone framework:

• MCP Protocol native: all 166 MCP tools are registered natively — no custom client, no API wrapper

• Hook-driven lifecycle: 12 CC lifecycle events (SessionStart → PreCompact) provide deep integration without modifying CC internals

• Agent templates as .md files: Installed to ~/.claude/agents/ (global) or .claude/agents/ (project-level) — CC's native agent system, not a custom abstraction

• Zero external dependencies at runtime: No external API calls, no cloud services — runs entirely within your CC subscription

• Context-aware: Session bootstrap injects only 5 core rules (down from 23) to minimize context budget impact, with subagent context capped at 60 lines

MCP Tools

The tables below are a curated selection — the full inventory lives in src/aiteam/mcp/tools/ and is machine-counted by scripts/check_readme_numbers.sh.

Team Management

Agent Management

Task Management

Pipeline Orchestration (Legacy — retired in v1.7.0, tools still registered, data read-only)

Loop Engine

Meeting System

Channel Communication

File Lock & Workspace Isolation

Git Automation

Debate System

Guardrails

Execution Patterns

Intelligence & Analysis

Memory System

Knowledge Layer (v1.8.0)

Model Governance (v1.8.1)

Trust & Reliability

Analytics

Briefing System

Reports (Database-backed)

Scheduler

Ecosystem Research (46 tools)

The single largest tool family — the full research funnel from scan to integration:

Integrations & Cross-Project

Prompt Registry

Project Management

System Operations

Agent Template Library

25 ready-to-use professional Agent templates with recommendation engine, covering a complete software engineering team. Templates are installed to plugin/agents/ (project-level) and ~/.claude/agents/ (global, available across all projects).

Engineering (13 templates)

Testing (4 templates)

Research & Support (3 templates)

Management (2 templates)

Debate Roles (2 templates)

Utility (1 template)

Roadmap

Completed

• Core Loop Engine (LoopEngine + Task Wall + Watchdog + Review)

• Failure Alchemy (Antibody + Vaccine + Catalyst)

• Decision Cockpit (Event stream + Timeline + Intent inspection)

• Event-driven Task Wall 2.0 (Real-time push + Intelligent matching)

• Living Team Memory (Knowledge query + Experience sharing)

• What-If Analyzer (Multi-option comparison)

• 8 structured meeting templates with keyword auto-select

• 25 professional Agent templates (23 base + 2 debate roles) with recommendation engine

• 4-layer defense rule system (48+ rules) + behavioral enforcement

• Dashboard Command Center (React 19) — 22 pages including the /workflows swimlane, Workflow detail, the Ecosystem suite, and Settings with model governance

• 166 MCP tools across 24 modules

• CC Workflow observability layer (auto-tracking + /workflows dashboard + workflow_list / workflow_get / workflow_reconcile)

• Knowledge layer — zero-LLM reference graph + unified 3-arm RRF search (v1.8.0)

• Model governance — transcript-based model discovery + global default startup model (v1.8.1)

• Machine-checked red-line invariants + one-command preflight (scripts/preflight.sh)

• AWARE loop memory system

• find_skill 3-layer progressive discovery

• task_update API for programmatic task management

• Workflow pipeline orchestration (7 templates + auto phase progression) — retired in v1.7.0, superseded by CC Workflow observability

• 1,758 automated tests, CI green

• Prompt Registry (version tracking + effectiveness metrics)

• BM25 as the main memory-retrieval chain (pure-Python Okapi BM25, Chinese bigram, recency-window recall + rerank)

• Event log enhancement (entity_id / entity_type / state_snapshot fields)

• CC Plugin Marketplace submission

• File lock / workspace isolation (acquire/release/check/list + TTL=300s)

• Channel communication system (team:/project:/global + @mention)

• Execution pattern memory (success/failure recording + BM25 retrieval)

• Git automation tools (git_auto_commit / git_create_pr / git_status_check)

• Guardrails L1 (7 dangerous patterns + PII warnings)

• Alembic database migration system

• Debate mode (4-round structured debate + code review)

• Agent trust scoring system (auto-adjust on task success/failure)

• Tool tier draft (informational CORE/ADVANCED grouping — groundwork for context budgeting)

• Agent Watchdog heartbeat system (5-min TTL timeout detection)

• SRE error budget model (GREEN/YELLOW/ORANGE/RED 4-level response)

• Completion verification protocol (anti-hallucination completion check)

• Ecosystem integration recipes (GitHub/Slack/Linear/Full-stack presets)

• Session bootstrap rule compression (23 → 5 core rules, 60% context reduction)

• Atomic API startup lock (multi-session port conflict prevention)

• Auto port discovery (API finds available port, writes to api_port.txt)

• MCP HTTP Streamable endpoint (/mcp/ on FastAPI)

• PyPI release — frozen at 1.2.0 and deprecated (install via plugin or source instead)

• INSTALL.md CC-assisted installation guide

In Progress / Planned

• Multi-tenant isolation

• Production validation and performance optimization

• Claude Code Plugin Marketplace listing

• Full integration test suite

• Documentation site (Docusaurus)

• Video tutorial series

Project Structure

ai-team-os/
├── src/aiteam/
│   ├── api/           — FastAPI REST endpoints (217 routes)
│   ├── mcp/
│   │   ├── server.py  — MCP server entry point
│   │   └── tools/     — 24 tool modules (166 MCP tools)
│   │       ├── agent.py, analytics.py, briefing.py, channels.py,
│   │       ├── ecosystem.py, error_budget_tool.py, file_lock.py,
│   │       ├── git_ops.py, guardrails.py, infra.py, links.py, loop.py,
│   │       ├── meeting.py, memory.py, pipeline.py, project.py,
│   │       ├── reports.py, scheduler.py, task.py, task_analysis.py,
│   │       ├── team.py, trust.py, watchdog.py, workflows.py
│   │       └── __init__.py  — Tool tier draft (informational)
│   ├── loop/          — Loop Engine
│   ├── meeting/       — Meeting system
│   ├── memory/        — Team memory
│   ├── orchestrator/  — Team orchestrator
│   ├── storage/       — Storage layer (SQLite, WAL journaling)
│   ├── templates/     — Agent template base classes
│   ├── hooks/         — CC Hook scripts (12 lifecycle events)
│   └── types.py       — Shared type definitions
├── plugin/
│   ├── agents/        — 25 Agent templates (.md)
│   └── .claude-plugin/ — Plugin manifest
├── dashboard/         — React 19 frontend (22 pages)
├── scripts/           — preflight + machine-checked invariants (incl. README number check)
├── docs/              — Design documents + ecosystem recipes
├── tests/             — Test suite (1,758 tests)
├── install.py         — One-click install script
└── pyproject.toml

Contributing

Contributions are welcome! We especially appreciate:

• New Agent templates: If you have prompt designs for specialized roles, PRs are welcome

• Meeting template extensions: New structured discussion patterns

• Bug fixes: Open an Issue or submit a PR directly

• Documentation improvements: Found a discrepancy between docs and code? Please correct it

# Set up the development environment
git clone https://github.com/CronusL-1141/AI-company.git
cd AI-company
python3 install.py

# One command = every gate CI runs (ruff + eslint + unit tests + machine-checked invariants)
bash scripts/preflight.sh

Before submitting a PR, make sure bash scripts/preflight.sh passes — it runs the exact gates CI enforces: ruff, eslint, the unit test suite, and the red-line invariant checks in scripts/check_invariants.sh. Every one of those invariants (hook copy sync, version lockstep, dist consistency, venv ban, README number drift) was distilled from a real incident in this repo's history — please keep them green.

License

MIT License — see LICENSE

AI Team OS — The AI company that runs while you sleep.

Built with Claude Code · Powered by MCP Protocol

Docs · Issues · Discussions