How to watch an agent improve its own setup in 5 minutes, no API key with harness2

Authorization notice. harness2 is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forCurious developer who saw Harness2 trending and wants proof it runs before investing in setup

The problemYou cannot tell whether a self-improving harness framework actually works without wiring up models and paying for API calls.

The outcomeA runs/demo folder showing parallel and sequential recursion with deterministic editors, produced locally in seconds.

What you need first

• Linux, Python 3.12 and uv for installation
• No credentials needed for the local demo (harness2-demo)
• Model-backed runs need Node.js 20+, the Google Cloud CLI, a Vertex AI project and model IDs in .env, and gcloud application-default login
• LAB needs Pandoc and Poppler; WorkBuddy-Bench needs Docker
• Model-backed benchmark runs incur API costs

Steps

1. Create the environment: uv venv --python 3.12 .venv
2. Activate it: source .venv/bin/activate
3. Install the package: uv pip install -e '.[render]'
4. Run the demo: harness2-demo --output runs/demo --k 2
5. Open the runs/demo folder and read the adopted harnesses and reflection notes.

Prompt for your agent

Clone google-research/harness2, set up a Python 3.12 uv environment, install it, and run harness2-demo with --k 2 into runs/demo. Summarize what files were produced and verify the demo ran without any model credentials.

Caveat. The demo uses deterministic editors, not real models, so it shows the mechanics of the loop and says nothing about real-world score gains.

• Markdown version
• JSON version