Captain Claw

Command a fleet of AI agents

Most AI tools give you one agent in a chat box. Captain Claw Flight Deck is a multi-agent command center — spawn specialist teams, run seven orchestration modes, ship software with Code (a plan → build → independent-review pipeline), and compose deterministic Flows. Self-hosted, MIT licensed, and works with every major LLM provider (or 100% local with Ollama). Since 0.8.0 it is safe for a whole team, with agents in your inbox and on your glasses — and 0.8.1 gives that team a complete kiosk and three M5Stack devices you talk to.

🌐 Website · 🚀 Live Demo · 📖 Docs · 📦 PyPI · 📝 0.8.1 release notes

A self-hosted framework for orchestrating fleets of specialist AI agents — from ensemble reasoning (seven orchestration modes) to a full agentic coding pipeline (plan → independent review → ship). Model-agnostic and local-friendly: connect OpenAI, Anthropic, Google Gemini, DeepSeek, Ollama, or OpenRouter (plus "Sign in with ChatGPT" and Google subscription text through the Antigravity CLI — no API key), or run 100% local with Ollama. Backed by 57 built-in tools per agent, persistent cross-session memory, and autonomous "dream cycle" cognition.

🎙️ NEW in 0.8.1: three devices that listen — and keep notes when you're offline

Push-to-talk Captain Claw clients on three M5Stack devices — the StickS3 (240×135 LCD), the StopWatch (466×466 round AMOLED with a clock face, touch and vibration) and the PaperColor (a 4" colour e-paper dashboard with two status lights and a room sensor). Press, talk, press again — or just stop talking: Flight Deck transcribes it, one of your agents answers, and the device speaks the answer sentence by sentence while the model is still writing it, the text following the voice. Out of Wi-Fi it keeps voice notes and sends them when the deck is back; hold the button for note-taking mode. Every question carries the battery, the room's temperature and the local time; the watch wears any picture you send the agent as its background; and all three take signed over-the-air updates from your own deck. One firmware tree: cd firmware/device && pio run -e stopwatch -t upload (or -e sticks3, -e papercolor_b). Details in firmware/device/README.md.

🧭 NEW in 0.8.1: a kiosk for everyone

The chat-first view your team's non-admins live in is now a complete place to work: a getting-started guide, one-click "What can I do?" skill cards, a File library and a Data library that summarise everything the agents keep, Scheduled tasks that deliver to chat, email or Telegram, one timeline per agent with named topics, a reasoning-effort picker, and a ⋯ menu per agent for its model, instructions and settings. Admins get an Admin console, invitations by email, a waitlist that answers applicants, branding and daily plan limits. See What's New in 0.8.1.

0.8.0, the release before, made Flight Deck safe for a team (every route knows who is calling, per-user Google and Microsoft, shared agents, team keys), put agents in your inbox behind guards that stop them inventing a send, added a HUD for Meta Ray-Ban Display, Claude driving your fleet over MCP, and Bat, a mode that keeps going until an independent judge says the work is done. See What's New in 0.8.0.

💻 Code — an engineering department, not a coding assistant

Describe what you want built. A router sizes the job; big work runs plan → your approval → build → three independent reviewers in parallel → triage → capped fix loop, every phase a git commit in the folder's own repo. Agents query a persistent Code Map (symbols + architecture, git-hash-fresh) instead of re-reading your tree; per-turn token costs are shown in chat; the whole process exports as one auditable Markdown transcript. Works on fresh folders or your existing local repos linked in — on any models you configure, including a cheap implementer with a premium reviewer.

Cursor and Claude Code give you one very good agent that plans, writes, reviews, and tests in a single context. Code splits those roles across independent agents — the reviewer never grades its own homework, QA actually runs the tests — and puts you at the approval gate before anything is built. Self-hosted, model-agnostic, no lock-in. A complete real run (an RTS game with 185 tests, ~$2.50 on DeepSeek) ships in examples/code/. Details in RELEASE_NOTES_0.7.0.md and USAGE.md.

Pick the right shape for the problem

One agent isn't always the answer — and one orchestration strategy never is. Captain Claw ships seven distinct modes, each tuned to a different kind of work.

🛠️ Agent Forge — describe a goal, an LLM designs the whole team (roles, models, tools, SOPs)	🏛️ Agent Council — specialists deliberate across moderated rounds, then vote and synthesize
🔀 Basna — N agents answer the same question blind, merged by reliability into one high-confidence result	🤝 Vatra — a team collaborates on a shared blackboard, each owning sections, improving over review rounds

The fifth mode is 💻 Code (above) — a plan-gated, independently-reviewed engineering pipeline. The sixth is Flight Deck itself — spawn, monitor, and coordinate the whole crew from one dashboard. The seventh, new in 0.8.0, is 🦇 Bat — the stubborn finisher: checkpointed steps with retries, survives restarts, and stops only when an independent, fail-closed judge says the task is done.

More than orchestration

⚙️ Flows — a deterministic automation DSL (triggers, gosub, parallel spawn/join, on error), validated by a parser, not interpreted by an LLM	🔭 Observatory — it keeps thinking when you're away: a live, auditable stream of thoughts, dreams, and standing intentions

• Plan Mode & Deep Mode — for when "probably right" isn't good enough: a reviewable DAG of verified steps, and frontier-quality answers via multiple rollouts + self-consistency voting + diverse-lens critics.
• 6-layer shared memory — working, semantic (vector + BM25), deep (full-text), insights, autonomous nervous system, and self-reflection — carried across sessions and across every agent.
• Shared Virtual File System — a host-sandboxed, per-user workspace the whole fleet reads and writes, with per-file authorship.
• 31 ready-made specialists — an editable archetype library spanning research, writing, engineering (a full coding family: planners, implementers, debugger, reviewers, QA, git operator, cartographer), data, ops, finance, and multimedia.

See it in action

⭐ Star the repo

Captain Claw is MIT licensed and free forever — your data stays on your machine, bring your own keys or run 100% local with Ollama. It's built solo and growing fast