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:
- start Ollama or LM Studio
- rerun
harness doctor - 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