Getting Started

Installation

macOS

curl -L https://github.com/conductor/conductor/releases/latest/download/conductor-darwin-arm64 -o conductor
chmod +x conductor
sudo mv conductor /usr/local/bin/

Linux

curl -L https://github.com/conductor/conductor/releases/latest/download/conductor-linux-amd64 -o conductor
chmod +x conductor
sudo mv conductor /usr/local/bin/

Provider Setup

Conductor needs an LLM provider to run workflows. Choose your preferred option:

Claude Code

If you have Claude Code installed:

conductor provider add claude-code

That’s it. Conductor uses your existing Claude Code authentication.

Ollama

For local models with Ollama:

# Start Ollama if not running
ollama serve

# Pull a model
ollama pull qwen3:8b

# Add the provider
conductor provider add ollama

See the Ollama guide for model recommendations by hardware.

Verify your setup:

conductor provider test

You should see a success message. Now you’re ready to run your first workflow.

First Workflow

Create a file hello.yaml:

name: hello
steps:
  - id: greet
    type: llm
    prompt: Say hello to the world in a creative way

Run it:

conductor run hello.yaml

You should see a creative greeting generated by your configured LLM.

Next Steps

• Tutorial - Build a complete meal planning workflow
• Providers - Provider configuration reference