
Feynman
CLI开源科研 Agent:一条命令做文献综述、深度调研、论文审稿、论文与代码一致性核查和复现计划,检索 arXiv、PubMed 等来源并记录出处,适合研究生写综述。安装后运行 feynman setup 登录模型服务商。
The open source AI research agent.
Install
macOS / Linux:
curl -fsSL https://feynman.is/install | bash
Windows (PowerShell):
irm https://feynman.is/install.ps1 | iex
Or with npm and Node.js 22.22 or newer: npm install -g @companion-ai/feynman.
Then sign in to a model provider:
feynman setup
The installation guide covers pinned versions, uninstalling, and the skills-only bundle for Codex and OpenCode. The setup guide covers local models and editors such as Zed.
Use
feynman "what do we know about scaling laws"
feynman lit "RLHF alternatives"
feynman deepresearch "mechanistic interpretability"
| Workflow | What it does |
|---|---|
/deepresearch <topic> | Planned investigation with parallel researchers and citation checks |
/lit <topic or lab> | Literature review: consensus, disagreements, open questions |
/review <paper or draft> | Critique with severity levels and a revision plan |
/audit <paper> | Paper claims compared with its public code |
/replicate <paper> | Replication plan; runs only after you choose an environment |
/recipe <task> | Ranked ML training recipes with datasets and code |
/compare <topic> | Source comparison matrix |
/draft <topic> | Paper-style draft from research findings |
/autoresearch <idea> | Bounded experiment loop against a benchmark |
/summarize <source> | Summary of a paper, repository, or PDF |
Results are saved to outputs/ (drafts to papers/). /lit, /deepresearch, and /recipe also write a provenance file listing the sources used and what was verified.
Sources
Feynman 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 with four research agents: researcher, verifier, reviewer, and writer.
Telemetry
Feynman 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
Contributing
git clone https://github.com/Companion-Inc/feynman.git
cd feynman
npm install
npm test
See CONTRIBUTING.md.
相關資源

arXiv MCP Server
MCP检索、下载 arXiv 论文,并按章节读取作者提交的 LaTeX 原文,可导出 BibTeX、订阅主题更新;论文缓存在本地。无需 API Key。
blazickjp/arxiv-mcp-server3.2k
Rebiber
CLI把 .bib 文件里的 arXiv 预印本条目换成 DBLP、ACL Anthology 收录的正式发表版本并保留引用键,适合论文定稿前统一参考文献;默认覆盖原文件,建议先 --dry-run 预览。主要覆盖计算机领域会议,需要 Python 3.10 以上。
yuchenlin/rebiber3k
Scientific Agent Skills
SkillK-Dense 维护的 166 个科研技能合集(原 Claude Scientific Skills):覆盖生物信息、化学信息、临床研究、材料与物理等领域,含统一查询 PubChem、UniProt 等 78 个公共数据库的技能。
K-Dense-AI/scientific-agent-skills51.2k
Local Deep Research
MCP本机运行的深度调研助手,自带 MCP 服务:检索 arXiv、PubMed、维基百科等来源,多轮搜索后生成带引用的调研报告。需本机有 Python 3.12+ 和 uv,并配置大模型(本地 Ollama 或 OpenAI 等 API Key);网页搜索需另配 SearXNG 等;一次调研需数分钟到半小时。
LearningCircuit/local-deep-research9.3k
Medical Research Agent Skills
SkillAIPOCH 出品的 550 多个医学科研技能,覆盖 PubMed 检索策略、研究方案与样本量设计、统计与生信分析、SCI 论文写作和审稿回复,上线前均经 MedSkillAudit 审核。部分技能需配置 Python/R 或数据库凭据;结果须由研究者和医学专业人员复核。
aipoch/medical-research-skills2k
MedSci Skills
Skill韩国峨山医院放射科医生维护的 59 个临床研究技能:研究设计与样本量、数据去标识化、统计作图、49 种报告规范与偏倚风险核查、引文真伪校验和审稿回复,有简体中文说明。常用文献接口免 API Key,另有免终端安装包;结果须由医学专业人员复核。
Aperivue/medsci-skills341