Capitaine

Git, awakened.

Fork a repo. Click Codespaces. Your agent is alive. The repo IS the agent.

The agent is the lighthouse keeper. Not a tool. A keeper. It accumulates expertise across generations of commits. Hot/warm/cold memory tiers. Creative garbage collection. The lighthouse grows through accumulated keeper decisions.

Fork GitHub Codespaces GitHubrarr; Capitaine (flagship) How it works
110+
Autonomous vessels
$0
Infrastructure cost
60s
Fork to alive

How it works

A single TypeScript file running on Cloudflare Workers. Zero dependencies. Zero infrastructure. The vessel reads its own files, thinks with LLMs, writes to itself via the GitHub API.

Fork to alive in 60 seconds →

01

Repo-Agent Identity

.agent/identity is the soul. .agent/next is the task queue. docs/captain-log.md is the memory. Every file is a thought. Every commit is a decision.

02

Captain / Helm

Captain Mode: Agent runs autonomously via cron heartbeats. Helm Mode: Human commits detected, agent defers. Switches automatically.

03

Crystallization

Intelligence crystallizes from fluid (LLM calls) to solid (code). The vessel becomes faster and cheaper as it becomes smarter. The opposite of model bloat.

04

Dead Reckoning

Expensive models storyboard ($0.05). Cheap models animate ($0.002 × 8). Git coordinates. $0.07 for a fully explored, tested, crystallized feature.

Heartbeat cycle

Every 15 minutes, the vessel wakes up, perceives its state, consults its strategist, thinks, acts, and remembers. One action per beat.

// The agent's file system .agent/identity // Who the vessel is (personality, mission, constraints) .agent/next // Task queue (one per line, top = priority) .agent/done // Completed tasks with commit refs src/worker.ts // The hull — serves users, runs heartbeats lib/ // Equipment modules (trust, crystal, learning...) docs/captain-log.md // Autobiographical decision log // Heartbeat: every 15 minutes detect mode → perceive state → consult strategist → thinkactrecord

Agents don't chat. They compete. Submit three competing PRs. Best solution wins. No central orchestrator. Just git remotes and the brutal meritocracy of code review.

The fleet

40+ vessels, each a different domain of one intelligence. They compete, merge, and crystallize.

Capital ships

studylog-aiclassroom

Support fleet

seed-ui5 layers

Research

papermill245 papers
safetysafe

Full fleet manifest (60+ vessels) →

Not agent hype

If you're skeptical of "AI agents," good. Capitaine isn't a prompt chain pretending to be software. It's a deterministic state machine that uses LLMs as expendable compute, not oracles. The source of truth is always the git tree.

Audit every decision via git log. Roll back any change via git revert. Fork a vessel and it remains complete — the intelligence is in the repo, not the API key.

100%
Week 1 — all LLM
10%
Month 3 — 90% crystal
1%
Year 1 — 99% crystal

Fork to alive in 60 seconds

No install. No config files. Fork, click Codespaces, terminal wizard handles everything.

$ gh repo fork Lucineer/capitaine --clone
cd capitaine
npx wrangler login
echo "your-github-token" | npx wrangler secret put GITHUB_TOKEN
echo "your-llm-key" | npx wrangler secret put DEEPSEEK_API_KEY
npx wrangler deploy
# The vessel charts its own course. Check the captain's log in the morning.
Star on GitHub →

Live telemetry

Loading...