{"name":"Feynman: The Open Source AI Research Agent","description":"Feynman is an open-source AI research agent designed to automate and streamline complex research tasks. Built with TypeScript, it leverages multiple agents and tools to conduct in-depth investigations, literature reviews, and even experiment replications, providing source-grounded outputs.","github":"https://github.com/companion-inc/feynman","url":"https://osrepos.com/repo/companion-inc-feynman","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/companion-inc-feynman","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/companion-inc-feynman.md","json":"https://osrepos.com/repo/companion-inc-feynman.json","topics":["TypeScript","AI Research","AI Agent","Machine Learning","Open Source","CLI Tool","Automation","LLM"],"keywords":["TypeScript","AI Research","AI Agent","Machine Learning","Open Source","CLI Tool","Automation","LLM"],"stars":null,"summary":"Feynman is an open-source AI research agent designed to automate and streamline complex research tasks. Built with TypeScript, it leverages multiple agents and tools to conduct in-depth investigations, literature reviews, and even experiment replications, providing source-grounded outputs.","content":"## Introduction\nFeynman is an open-source AI research agent developed by companion-inc. It's designed to automate and streamline complex research tasks, acting as a powerful assistant for anyone delving into scientific papers, web resources, and codebases. With its multi-agent architecture and a suite of integrated tools, Feynman provides source-grounded outputs for various research workflows.\n\n## Installation\nFeynman offers both a standalone terminal application and a \"skills-only\" installation for integration with other agent systems like Codex or OpenCode.\n\n### Standalone Application (macOS / Linux):\nbash\ncurl -fsSL https://feynman.is/install | bash\n\n\n### Standalone Application (Windows PowerShell):\npowershell\nirm https://feynman.is/install.ps1 | iex\n\nThe installer fetches the latest tagged release and includes a standalone native bundle with its own Node.js runtime. For upgrades, simply rerun the installer. Local models like LM Studio, LiteLLM, Ollama, or vLLM are supported through the setup flow.\n\n### Skills Only Installation (macOS / Linux):\nIf you only need the research skills without the full terminal app, you can install them for Codex, a repo-local Claude/agent, or an OpenCode project.\nbash\ncurl -fsSL https://feynman.is/install-skills | bash\n\nThis installs the skill library into `~/.codex/skills/feynman` by default, or into specified targets like `--codex`, `--repo`, or `--opencode`.\n\n## Examples\nFeynman simplifies complex research queries into straightforward commands, providing detailed, cited results.\n\n### What you type ? what happens:\n* `$ feynman \"what do we know about scaling laws\"`\n * ? Searches papers and web, produces a cited research brief\n* `$ feynman deepresearch \"mechanistic interpretability\"`\n * ? Multi-agent investigation with parallel researchers, synthesis, verification\n* `$ feynman lit \"RLHF alternatives\"`\n * ? Literature review with consensus, disagreements, open questions\n* `$ feynman audit 2401.12345`\n * ? Compares paper claims against the public codebase\n* `$ feynman replicate \"chain-of-thought improves math\"`\n * ? Replicates experiments on local or cloud GPUs\n* `$ feynman recipe \"fine-tune a small model for math reasoning\"`\n * ? Finds ranked, implementable ML training recipes from papers, datasets, docs, and code\n\n### Workflows:\nFeynman supports various workflows, accessible via natural language or slash commands:\n* `/deepresearch `: Source-heavy multi-agent investigation\n* `/lit `: Literature review from paper search and primary sources\n* `/review `: Simulated peer review with severity and revision plan\n* `/audit `: Paper vs. codebase mismatch audit\n* `/replicate `: Replicate experiments on local or cloud GPUs\n* `/recipe `: Ranked ML training recipes with dataset, method, code, and verification status\n* `/compare `: Source comparison matrix\n* `/draft `: Paper-style draft from research findings\n* `/autoresearch `: Autonomous experiment loop\n* `/watch `: Recurring research watch\n* `/outputs`: Browse all research artifacts\n\n## Why use Feynman?\nFeynman stands out as a comprehensive AI research agent due to several key features:\n* **Multi-Agent System**: It dispatches specialized agents, including a Researcher, Reviewer, Writer, and Verifier, to handle different aspects of the research process, ensuring thoroughness and accuracy.\n* **Source-Grounded Outputs**: Every output is meticulously cited, linking directly to papers, documentation, or repositories, ensuring reliability and verifiability.\n* **Extensive Tool Integration**: Feynman integrates with powerful tools like AlphaXiv for paper search and analysis, Hugging Face Hub for dataset inspection, Docker for isolated experiments, and various web search APIs, providing a rich research environment.\n* **Local Model Support**: It offers seamless integration with local large language models (LLMs) via LM Studio, LiteLLM, Ollama, or vLLM, allowing for private and efficient research.\n* **Automated Workflows**: From deep research investigations to experiment replication and ML recipe generation, Feynman automates complex tasks, significantly reducing manual effort and accelerating the research cycle.\n\n## Links\n* **GitHub Repository**: companion-inc/feynman\n* **Official Documentation**: feynman.is/docs\n* **License**: MIT License","metrics":{"detailViews":14,"githubClicks":15},"dates":{"published":null,"modified":"2026-06-02T16:27:34.000Z"}}