The open source AI research agent.
Feynman is an open-source AI research agent that helps users investigate topics with language models. It supports local model providers and hosted model authentication through its setup process. The catalogue contains skills, agents, and instructions that extend Feynman’s workflows.
This repository also configures its own agents. See what feynman tells them →
Skill Claude CodeCodex
Search, read, and query research papers via Feynman's alphaXiv-backed alpha tools. Use when the user asks about academic papers, wants to find research on a topic, needs to read a specific paper, ask questions about a paper, inspect a paper's code repository, or manage paper annotations.
Skill Claude CodeCodex
Predict or audit protein structures with AlphaFold2-style workflows. Use when a research task needs monomer/multimer structure prediction, MSA/template handling, confidence metrics, or comparison against PDB/AlphaFold references.
Skill Claude CodeCodex
Bounded research experiment loop that tries hypotheses, measures benchmark evidence, keeps what works, and records what fails. Use when the user asks to optimize a research metric, run an experiment loop, improve model/retrieval/evaluation performance iteratively, or benchmark a research hypothesis.
Skill Claude CodeCodex
Run or plan Boltz biomolecular structure predictions for proteins, complexes, ligands, or nucleic-acid assemblies. Use when a task asks for Boltz setup, inputs, outputs, confidence interpretation, or reproduction.
Skill Claude CodeCodex
Use Borzoi-style regulatory genomics models for sequence-to-expression or variant-effect analysis. Use when the task asks for noncoding variant impact, regulatory sequence design, or expression prediction.
Skill Claude CodeCodex
Run or prepare Chai-1 structure predictions for biomolecular complexes. Use when a task asks for Chai-1 inputs, multimers, ligand/nucleic acid structure prediction, or confidence review.
Skill Claude CodeCodex
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
Skill Claude CodeCodex
Contribute changes to the Feynman repository itself. Use when the task is to add features, fix bugs, update prompts or skills, change install or release behavior, improve docs, or prepare a focused PR against this repo.
Skill Claude CodeCodex
Configure Feynman specialists, skills, connectors, permissions, memory categories, compute providers, and project setup. Use when the task asks to customize the research workbench or create a reusable Feynman research capability.
Skill Claude CodeCodex
Run a thorough, source-heavy investigation on any topic. Use when the user asks for deep research, a comprehensive analysis, an in-depth report, or a multi-source investigation. Produces a cited research brief with provenance tracking.
Skill Claude CodeCodex
Run or plan DiffDock molecular docking workflows. Use when a task asks for protein-ligand pose prediction, docking setup, ligand/protein preparation, pose ranking, or docking-result verification.
Skill Claude Code
Execute research code inside isolated Docker containers for safe replication, experiments, and benchmarks. Use when the user selects Docker as the execution environment or asks to run code safely, in isolation, or in a sandbox.
Skill Claude CodeCodex
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
Skill Claude CodeCodex
Predict quick protein structures with ESMFold-style workflows. Use when a task needs fast MSA-free folding, sequence triage, variant structure screening, or confidence review.
Skill Claude CodeCodex
Use Evo2-style biological sequence models for generation, scoring, or variant-effect analysis. Use when a task asks about DNA/RNA/protein sequence likelihood, editing, design, or long-context biological modeling.
Skill Claude CodeCodex
Use ESM2 protein language models for embeddings, mutation scoring, remote homology, or representation analysis. Use when a task needs protein embeddings, zero-shot variant scores, clustering, or sequence-function triage.
Skill Claude CodeCodex
Compose a publication-grade multi-panel scientific figure from a claim, dataset, or draft result. Use when the task needs panel planning, consistent figure layout, figure review, or final figure assembly.
Skill Claude CodeCodex
Apply scientific plotting and figure-quality rules to a single plot or panel. Use when drawing, cleaning, labeling, or reviewing plots for research artifacts.
Skill Claude CodeCodex
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.
Skill Claude CodeCodex
Inspect visible research run state, scheduled research follow-ups when available, and durable watch artifacts. Use when the user asks what's running for a research workflow or wants research-run status.
Skill Claude CodeCodex
Design protein sequences around ligand or small-molecule contexts with LigandMPNN-style workflows. Use when a task asks for ligand-aware protein design, residue redesign, constraints, or design ranking.
Skill Claude CodeCodex
Run a literature review using paper search and primary-source synthesis. Use when the user asks for a lit review, paper survey, state of the art, or academic landscape summary on a research topic.
Skill Claude CodeCodex
Register or audit Feynman-managed model endpoints. Use when a research workflow needs a local or remote model service, endpoint health checks, credential refs, startup scripts, or inference routing.
Skill Claude CodeCodex
Find implementable ML training recipes from papers, datasets, docs, and code. Use when the user wants to fine-tune, train, reproduce, or choose a practical ML method, dataset, hyperparameter setup, or benchmark recipe.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: