feynman

The open source AI research agent

Investigate topics, write papers, run experiments, review research, audit codebases — every output cited and source-grounded

npm install -g @companion-ai/feynman

What you type → what happens

$feynman "what do we know about scaling laws"
Searches papers and web, produces a cited research brief
$feynman deepresearch "mechanistic interpretability"
Multi-agent investigation with parallel researchers, synthesis, verification
$feynman lit "RLHF alternatives"
Literature review with consensus, disagreements, open questions
$feynman audit 2401.12345
Compares paper claims against the public codebase
$feynman replicate "chain-of-thought improves math"
Asks where to run, then builds a replication plan

Workflows

Ask naturally or use slash commands as shortcuts.

/deepresearch

Source-heavy multi-agent investigation

/lit

Literature review from paper search and primary sources

/review

Simulated peer review with severity and revision plan

/audit

Paper vs. codebase mismatch audit

/replicate

Replication plan with environment selection

/compare

Source comparison matrix

/draft

Paper-style draft from research findings

/autoresearch

Autonomous experiment loop

/watch

Recurring research watch

Agents

Four bundled research agents, dispatched automatically.

Researcher

Gathers evidence across papers, web, repos, and docs

Reviewer

Simulated peer review with severity-graded feedback

Writer

Structured briefs and drafts from research notes

Verifier

Inline citations and source URL verification

Tools

Paper search, Q&A, code reading, persistent annotations

Isolated container execution for safe local experiments

Secure cloud execution for GPU workloads and long-running research

Web search

Gemini or Perplexity, zero-config default

Session search

Indexed recall across prior research sessions

Preview

Browser and PDF export of generated artifacts

Built on Pi, alphaXiv, and Agent Computer. MIT licensed. Open source.