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
Workflows
Ask naturally or use slash commands as shortcuts.
Source-heavy multi-agent investigation
Literature review from paper search and primary sources
Simulated peer review with severity and revision plan
Paper vs. codebase mismatch audit
Replication plan with environment selection
Source comparison matrix
Paper-style draft from research findings
Autonomous experiment loop
Recurring research watch
Agents
Four bundled research agents, dispatched automatically.
Gathers evidence across papers, web, repos, and docs
Simulated peer review with severity-graded feedback
Structured briefs and drafts from research notes
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
Gemini or Perplexity, zero-config default
Indexed recall across prior research sessions
Browser and PDF export of generated artifacts
Built on Pi, alphaXiv, and Agent Computer. MIT licensed. Open source.