Skip to main content

Quick Start

This is the intended standalone first-run flow.

1. Install Agent Harness

Download the platform installer from the download page and run it.

Once the installer completes, the harness CLI is available in your terminal.

Installers coming soon

Windows, macOS, and Linux installers are in development. Join the Discord to get early access as a beta tester.

2. Generate config

harness init --profile local

3. Validate setup

harness doctor

4. Inspect the built-in demo

harness demo --list-tasks
harness demo --dry-run --task ts-isUUID

5. Run one task

harness run tasks/ts-lib/ts-isUUID.json --repo test-repos/ts-lib

6. Inspect results

harness status
harness report

7. Recover from the common failure

If the model endpoint is not reachable:

  1. start Ollama or LM Studio
  2. rerun harness doctor
  3. rerun the task

If you only want to validate local paths and config before services are up:

harness doctor --skip-model-endpoint --skip-agent-brain