explaingit

companion-inc/feynman

7,088TypeScriptAudience · researcherComplexity · 3/5Setup · moderate

TLDR

A command-line research agent that searches academic papers, web sources, and code repositories to produce cited research summaries, aimed at machine learning and AI researchers who want quick, structured answers.

Mindmap

mindmap
  root((feynman))
    What it does
      Research summaries
      Literature reviews
      Paper audits
      Experiment replication
    Built-in agents
      Researcher
      Reviewer
      Writer
      Verifier
    Integrations
      AlphaXiv
      Hugging Face Hub
      Docker
      Modal and RunPod
    Setup
      Single install command
      Local models supported
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Things people build with this

USE CASE 1

Get a cited research summary on any ML topic by typing a question into your terminal.

USE CASE 2

Generate a literature review that maps where academic sources agree and disagree on a subject.

USE CASE 3

Audit a research paper by checking whether its public codebase actually matches the claims it makes.

USE CASE 4

Reproduce paper experiments locally or on cloud GPU services with a single /replicate command.

Tech stack

TypeScriptNode.jsDockerOllamaLiteLLM

Getting it running

Difficulty · moderate Time to first run · 30min

Basic queries work without API keys using local models via Ollama or LM Studio, cloud GPU features require Modal or RunPod accounts.

In plain English

Feynman is an open-source command-line tool that acts as a research agent for scientific and machine learning topics. You give it a question or a research topic, and it searches through academic papers, web sources, and code repositories to produce a cited, source-grounded brief in return. It is designed primarily for people working in machine learning and AI research who want to move quickly from a question to a structured answer. The tool runs in your terminal and accepts both plain English questions and slash commands for specific workflows. Asking "what do we know about scaling laws" returns a research summary with citations. Running the /lit command on a topic produces a literature review that notes where sources agree and disagree. The /audit command takes a paper ID and checks whether the claims in the paper match the public codebase it references. The /replicate command attempts to reproduce experiments from a paper on your local machine or in cloud GPU environments. Four built-in agents work together behind the scenes. A Researcher gathers evidence from papers and documentation. A Reviewer applies simulated peer-review feedback with severity grades. A Writer produces structured drafts from collected notes. A Verifier checks inline citations, confirms source URLs, and removes broken links from the output. External integrations extend what the tool can reach. It connects to AlphaXiv for paper search and Q&A, the Hugging Face Hub for dataset and model inspection, Docker for isolated experiment execution, and services like Modal and RunPod for GPU compute when an experiment needs more resources than a local machine can supply. Installation is a single curl or PowerShell command on macOS, Linux, or Windows. If you only want the research skill library without the full terminal application, a separate installer is available for that subset. The project also supports local AI models through LM Studio, Ollama, or a LiteLLM proxy, so you do not need cloud API keys to run basic queries.

Copy-paste prompts

Prompt 1
Using the Feynman CLI, give me a cited research summary on scaling laws in large language models.
Prompt 2
Run /lit on 'diffusion models vs GANs' and produce a literature review noting where sources agree and disagree.
Prompt 3
Run /audit on paper ID [arxiv-id] and tell me whether the claims match the referenced public codebase.
Prompt 4
Using /replicate, set up and run the experiments from this paper on a Modal cloud GPU.
Prompt 5
Configure Feynman to use a local Ollama model as the backend so I can run basic queries without any cloud API keys.
Open on GitHub → Explain another repo

← companion-inc on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.