CrewHaus Factory

The open-source meta-harness compiler for AI agents.

Compile a single spec (a crewhaus.yaml) into a CLI agent, channel bot, RAG pipeline, multi-agent crew, eval harness, voice/realtime agent, browser/computer-use agent, and more. Active eval optimization. Trust-aware by default. Apache-2.0.

★ If CrewHaus is useful to you, star the repo. For an independent, Apache-2.0 project maintained in the open, a star is the clearest signal the work is worth continuing.

# Install the standalone binary — no runtime required:
brew tap crewhaus/tap && brew install crewhaus          # macOS / Linux (Homebrew)
# Windows: scoop install crewhaus · winget install CrewHaus.CLI
# Debian/Ubuntu (apt) and npm/Bun: see "Install" below

crewhaus --version
crewhaus init my-agent
cd my-agent
crewhaus compile crewhaus.yaml -o build && crewhaus run crewhaus.yaml

crewhaus is open source under Apache-2.0 and published as a bare package on npm, Homebrew, Scoop, winget, and apt — see Install.

Install

The fastest path is the self-contained binary — one file, no Bun/Node required:

# macOS / Linux (Homebrew)
brew tap crewhaus/tap && brew install crewhaus

# Windows (Scoop)
scoop bucket add crewhaus https://github.com/crewhaus/scoop-bucket
scoop install crewhaus

# Windows (winget)
winget install CrewHaus.CLI

# Debian / Ubuntu (apt)
curl -fsSL https://crewhaus.github.io/apt/key.gpg | sudo gpg --dearmor -o /usr/share/keyrings/crewhaus.gpg
echo "deb [signed-by=/usr/share/keyrings/crewhaus.gpg] https://crewhaus.github.io/apt stable main" | sudo tee /etc/apt/sources.list.d/crewhaus.list
sudo apt update && sudo apt install crewhaus

Prefer npm? The crewhaus package runs on Bun ≥ 1.2:

npm install -g crewhaus        # global
bun add -d crewhaus            # project-local dev dependency

Then confirm your install:

crewhaus --version

You can also grab a binary directly from the GitHub Releases page.

Why CrewHaus?

Write the agent once, as a spec (crewhaus.yaml). Compile it to the shape each situation calls for — a CLI to run locally, a Slack bot for the team, an eval bundle to grade it — each emitted as code idiomatic to that runtime, not a generic wrapper.

When the spec changes, every shape recompiles. Run the eval loop and crewhaus optimize rewrites the spec from its failures, so the fix lands in all of them. CrewHaus is the layer above the runtimes.

What you can compile to

These target shapes ship today:

Target	What it produces
cli	A self-contained TypeScript CLI agent
channel (slack / discord / telegram / whatsapp / imessage)	Channel bots
graph	A stateful graph runtime
pipeline	A RAG pipeline
crew	A multi-agent crew
research	An autonomous research agent
batch	A batch worker
voice	A voice/realtime agent
browser	A browser/computer-use agent
managed	A managed multi-tenant runtime
eval	An eval bundle for grading other targets
workflow	A workflow orchestration runtime
onchain	An on-chain (EVM) agent runtime
onchain-game	An on-chain game runtime

Adding a new target shape starts at the IR, not at codegen. See COMPILER-ARCHITECTURE.md.

The three pillars

1. The compiler is the protagonist. Specs flow through parseSpec → lower → applyPasses → emit. The IR is a discriminated union of target-shape variants; each emitter consumes its own typed variant.

2. Eval is active, not passive. Eval failures produce spec patches. crewhaus optimize searches the mutation space (rule-based or Claude-driven) and writes back through a YAML CST that preserves comments and key order. The loop closes.