Look twice.Find the gem.

AI agents and MCP servers, each published with its source and what the checks found.

Marketplace

  • Everything
  • AI agents
  • Apps
  • MCP servers
  • Templates
  • What people want
  • What changed this week
  • The verification standard
  • The ooruby Index
  • Servers that publish no source
  • Reliability guides
  • What the catalogue holds
  • Sell here

Our library

  • Everything, in one place
  • Guides
  • Glossary
  • Calculators
  • Checklists and cheat sheets
  • Community

ooruby

  • Home
  • For teams
  • Site status
  • Company projects
  • RSS feed

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.

AI agentsAppsMCP serversTemplatesWantedCommunityOur library
Sign inSell
Catalogue/Agents/Feynman

Feynman

companion-ai · Agent

Feynman is a research-first command line agent built on Pi and alphaXiv. You give it a topic or a paper and pick a workflow: a planned investigation with parallel researchers and citation checks, a literature review, a critique with a revision plan, a comparison of a paper's claims with its public code, a replication plan, or a paper-style draft. It searches academic sources and the web, reads local PDFs and documents, and saves its results to an outputs folder.

Written by ooruby from the README of @companion-ai/feynman 0.5.34.

Not claimed by its maker. Is this yours? Prove it and answer the findings

Why it's useful

It gives you a research agent that plans an investigation, checks citations and records which sources it used and verified.

What you could do with it

  1. 1Ask for a literature review on RLHF alternatives and get consensus, disagreements and open questions.
  2. 2Run a deep research pass on a topic and read the provenance file that lists the sources it used.
  3. 3Compare a paper's claims with its public code using the audit workflow.

Written from its documentation: what it says it can do, not what our checks found.

FEagentResearch

Maintenance

Not measured

No release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.

Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured

Not yet tested
Command execution is bounded
inventory
node child_process (scripts/check-pi-rpc.mjs:5)
node child_process (extensions/research-tools/header.ts:3)
synchronous shell execution (extensions/research-tools/header.ts:150)
synchronous shell execution (extensions/research-tools/header.ts:157)
An inventory of where the code starts another program, not a verdict on this row: whether each one runs a fixed program or whatever it is handed takes a reading by hand.

Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.

What this does not cover

  • ·Everything. Treat it as you would software from anywhere else.

Receipt history: every signed receipt for every version of this listing, and what changed between them.

In its maker's words

Research-first CLI agent built on Pi and alphaXiv

Compare with

  • Modsearchside by side
  • Pi Web Accessside by side
  • Ghostgetside by side
Compare all 4

How far this has been checked

Static scanned

What it establishes
Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
What it does not
How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
Exactly what was read
Version 0.5.34, the file with digest sha512-Iz6jxOwHTM2vP99G3mXtxLiLWHuTp8bJyR6efG9GWBwX2UE7KQ+ta3bULsfEETwZFmCBBfSIB1DX6FnKQiyVEw==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
Authentication
Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
How the rungs work

Adding it

Run it with:

npx -y @companion-ai/feynman@0.5.34

Pinned to 0.5.34, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.

Where this came from

Registry
npm
Package
@companion-ai/feynman
Version read
0.5.34
Resolved
2026-10-10
Open the source(opens in a new tab)

Built from source, attested

npm publishes a signed statement that this exact package was built from the repository below, at this commit. It is verifiable without taking our word for it.

Repository
github.com/companion-inc/feynman
Commit
383af20af4b0
Built by
github.com/actions/runner/github-hosted
Registry publish attestation
signed by npm · 2026-10-10
Checked
2026-10-10

The badge, if this is your listing

It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.

[![ooruby: static scanned](https://ooruby.com/api/badge/companion-ai-feynman)](https://ooruby.com/market/companion-ai-feynman)

About this listing

Kind
Agent
Category
Research
Pricing
Free
Sandbox
No
Hosted
No
Updated
2026-10-10
Price
Free
Get it freeVisit maker
Rating
no reviews yet
0 want this so far
Sign in to vote

Sign in to watch this listing and hear when its version, rung or findings change.

More from companion-ai

See the storefront
AHagentResearch
4 findingsStatic scanned
An unofficial client that signs you in to alphaXiv through your browser. It also ships a stdio MCP server and library helpers for searching papers, getting a paper, asking about a paper, annotations and sign-in.

Alpha Hub

companion-ai
Free

Searches research papers, fetches them and asks questions about them through alphaXiv from a terminal.

5.7k installs/moMIT

Similar agents

All agents
MOagentResearch
4 findingsStatic scanned
By default it searches through Firecrawl's keyless tier, with no account or API key. Add keys for Tavily, Exa or Firecrawl and it fails over between engines when one fails or runs out of quota.

Modsearch

liustack
Free

Gives coding agents on models like DeepSeek and GLM web search, X search and page fetching.

41.4k installs/moMIT
PWagentResearch
4 findingsStatic scanned
Search works through Exa without an API key by default, but video questions need a Gemini API key or opt-in browser cookies, and frames need ffmpeg, plus yt-dlp for YouTube. The tools can also run as a local MCP server for other agents.

Pi Web Access

nicopreme
Free

Gives the Pi coding agent web search, page and PDF fetching, GitHub cloning and YouTube video questions.

693.5k installs/moMIT
OPagentResearch
6 findingsStatic scanned
Built for scientific and ML engineering work, the agent writes and runs code and queries scientific databases. Bring your own API key, use eligible ChatGPT or Codex access, or run a local model.

Openscience

synsci
Free

Runs an AI research agent in your browser that plans tasks, runs experiments and writes up results.

30.3k installs/moNo licence

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.