Feynman — The open source AI research agent

The open source AI
research agent

Reads papers, searches the web, writes drafts, runs experiments, and cites every claim. All locally on your computer.

What you type → what happens

Ask a question or run a workflow. Every answer is cited.

feynman "what do we know about scaling laws" Cited research brief from papers and web

feynman deepresearch "mechanistic interpretability" Multi-agent deep dive with synthesis and verification

feynman lit "RLHF alternatives" Literature review with consensus and open questions

feynman audit 2401.12345 Paper claims vs. what the code actually does

feynman replicate "chain-of-thought improves math" Replication plan, compute target, experiment execution

Workflows

Slash commands or natural language. Your call.

/deepresearch

Multi-agent investigation across papers, web, and code

/lit

Literature review from primary sources with consensus mapping

/review

Simulated peer review with severity scores and a revision plan

/audit

Paper-to-code mismatch audit for reproducibility claims

/replicate

Replication plan and execution in a sandboxed Docker container

/compare

Side-by-side source comparison with agreement and conflict matrix

/draft

Polished paper-style draft with inline citations from findings

/autoresearch

Autonomous loop: hypothesize, experiment, measure, repeat

/watch

Recurring monitor for new papers, code, or product updates

Agents

You ask a question. The right team assembles.

Researcher

Hunts for evidence across papers, the web, repos, and docs

Reviewer

Grades claims by severity, flags gaps, and suggests revisions

Writer

Structures notes into briefs, drafts, and paper-style output

Verifier

Checks every citation, verifies URLs, removes dead links

Skills & Tools

How Feynman searches, remembers, and exports work.

AlphaXiv

Paper search, Q&A, code reading, and annotations via the alpha CLI

Web search

Searches via Gemini or Perplexity

Session search

Indexed recall across prior research sessions

Preview

Browser and PDF export of generated artifacts

Compute

Run experiments locally or burst onto managed GPU infrastructure when needed.

Docker

Isolated local containers for safe experiments

Modal

Serverless GPU compute for burst training and inference

RunPod

Persistent GPU pods with SSH access for long-running runs