\n\n## Install\n\nmacOS / Linux:\n\n```bash\ncurl -fsSL https://feynman.is/install | bash\n```\n\nWindows (PowerShell):\n\n```powershell\nirm https://feynman.is/install.ps1 | iex\n```\n\nOr with npm and Node.js 22.22 or newer: `npm install -g @companion-ai/feynman`.\n\nThen sign in to a model provider:\n\n```bash\nfeynman setup\n```\n\nThe [installation guide](https://feynman.is/docs/getting-started/installation) covers pinned versions, uninstalling, and the skills-only bundle for Codex and OpenCode. The [setup guide](https://feynman.is/docs/getting-started/setup) covers local models and editors such as Zed.\n\n## Use\n\n```bash\nfeynman \"what do we know about scaling laws\"\nfeynman lit \"RLHF alternatives\"\nfeynman deepresearch \"mechanistic interpretability\"\n```\n\n| Workflow | What it does |\n| --- | --- |\n| `/deepresearch ` | Planned investigation with parallel researchers and citation checks |\n| `/lit ` | Literature review: consensus, disagreements, open questions |\n| `/review ` | Critique with severity levels and a revision plan |\n| `/audit ` | Paper claims compared with its public code |\n| `/replicate ` | Replication plan; runs only after you choose an environment |\n| `/recipe ` | Ranked ML training recipes with datasets and code |\n| `/compare ` | Source comparison matrix |\n| `/draft ` | Paper-style draft from research findings |\n| `/autoresearch ` | Bounded experiment loop against a benchmark |\n| `/summarize ` | Summary of a paper, repository, or PDF |\n\nResults are saved to `outputs/` (drafts to `papers/`). `/lit`, `/deepresearch`, and `/recipe` also write a provenance file listing the sources used and what was verified.\n\n## Sources\n\nFeynman searches alphaXiv, Semantic Scholar, OpenAlex, arXiv, PubMed, Europe PMC, bioRxiv, medRxiv, Crossref, the web, and Hugging Face, and reads local PDFs and documents. Free `OPENALEX_API_KEY` and `SEMANTIC_SCHOLAR_API_KEY` keys avoid the shared rate limits. It runs on stock [Pi](https://github.com/earendil-works/pi) with four research agents: researcher, verifier, reviewer, and writer.\n\n## Telemetry\n\nFeynman sends anonymous usage data to PostHog: commands, workflows, tools, models, token counts, and errors with their messages and stack traces (your home folder shown as `~`). It never sends prompts, model output, paper content, or tool arguments. Turn it off with `FEYNMAN_TELEMETRY=off`. [What is sent](https://feynman.is/docs/getting-started/configuration#telemetry)\n\n## Contributing\n\n```bash\ngit clone https://github.com/Companion-Inc/feynman.git\ncd feynman\nnpm install\nnpm test\n```\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md).\n\n[Docs](https://feynman.is/docs) · [Release notes](RELEASES.md) · [MIT License](LICENSE)\n","readmeFilename":"README.md"}
![\"Feynman](\"assets/hero.png\")
\n \n![\"Docs\"](\"https://img.shields.io/badge/docs-feynman.is-0d9668?style=flat-square\"){kind=icon}
![\"License\"](\"https://img.shields.io/github/license/Companion-Inc/feynman?style=flat-square\")
![\"Ask](\"https://deepwiki.com/badge.svg\"){kind=icon}
\n