louped 0.1.2

A local workbench for research on LLM behavior and efficiency.

Docs • Architecture • Roadmap • Contributing

Keep your research questions about language models in a project. Each question is an experiment with a README (the question and the test) and a script that runs it. Your coding agent writes and runs them; you read the results item by item in louped's app. Everything runs on your machine or your cluster, with open-weight models.

Start

pip install 'louped[server,tracking,interp,agent]'
louped init my-research && cd my-research
louped serve

Open http://127.0.0.1:8000 and launch the example experiment.

How it works

1. Make a project with louped init. It also connects your coding agent.
2. Ask a question. Your agent (Claude Code, Codex, Cursor) writes the experiment.
3. Run it on your machine, or send it to a Slurm cluster and import the results.
4. Read the results: every item under every condition, what changed, and out of how many.

Already have results? louped view <folder> opens them read-only.

See the docs for writing experiments, changing models, using your agent and running on a cluster.

Develop

You need just, uv and Node 22 with pnpm.

just bootstrap     # install everything and the git hooks
just check         # lint, types, tests, and the app and site builds
just serve         # the app on :8000

License

Apache 2.0