Skip to main content
Fabro has two modes:
  • Standalone mode — Run workflows directly from the CLI. This is what the quick start covers below.
  • Server mode — An API server with a web UI for launching and managing workflow runs at scale. See Server Mode for details.

​
Supported platforms

OSArchitectureSupported
Linuxx86_64Yes
Linuxarm64 (aarch64)Yes
macOSarm64 (Apple Silicon)Yes
macOSx86_64 (Intel)No
WindowsanyNo
On Intel Macs, run Fabro in a Linux x86_64 container or VM. Native Windows isn’t supported; use WSL2 with a supported Linux architecture.

​
Install

curl -fsSL https://fabro.sh/install.md | claude
Release binaries and the multi-arch Docker image ship with SLSA Build Provenance attestations you can verify with gh attestation verify.
Setting up server mode instead? Run fabro server start to finish setup in a browser-based wizard. See Running the Fabro Server for the full flow.

​
Initialize your project

cd my-repo/
fabro repo init
This creates .fabro/project.toml and a starter workflow under .fabro/workflows/hello/.

​
Configure API keys

Add at least one LLM provider key: 
ANTHROPIC_API_KEY=sk-ant-...
OPENAI_API_KEY=sk-...
GEMINI_API_KEY=AI...
You only need one provider key to get started. Add more to enable multi-model workflows.

​
Run your first workflow

fabro run hello

​
Next steps

Why Fabro?

Understand the problems Fabro solves.

Workflows

Learn how to define workflow graphs in Graphviz.