companion-inc/feynman
Feynman
Feynman is an open-source AI research agent that coordinates multi-agent workflows to search papers, run experiments, and produce cited research briefs. It orchestrates parallel researcher agents that independently investigate subtopics, then synthesizes and verifies findings through a multi-step orchestration loop, enabling deep research across academic papers, web sources, and code.
The tool distinguishes itself through several specialized capabilities, including paper claim verification that audits research paper claims against actual code implementations to identify mismatches and validate results, and a replication planning engine that generates step-by-step plans for reproducing research results with environment selection and compute target configuration. It also functions as a literature review generator, producing structured reviews with cited references covering consensus, disagreements, and open questions on a given topic, and includes a Hugging Face Hub inspector for reading dataset metadata and accessing files from model, dataset, and Space repositories.
Beyond these core differentiators, Feynman supports a broad range of research activities such as paper and web search, cited research brief generation, full-text paper access resolution, paper reading priority ranking, multi-source comparison, ML training recipe discovery, and research paper drafting. It manages research sessions with indexing and search for prior session recall, and can execute bounded experiment loops with benchmark evidence to answer research questions. The tool also provides artifact browsing and preview, system performance observation, and the ability to set up research watches with optional follow-up schedules.
Installation is available via npm into an existing Node.js environment, as a standalone native bundle for macOS, Linux, or Windows with zero external dependencies, or as a research skills-only download for use with Codex or other agents. A guided setup wizard walks through model provider selection, authentication, and optional research-continuity extras like memory or session search.
Features
- Research Agents - An open-source tool that coordinates multi-agent workflows to search papers and produce cited briefs.
- Agent Orchestration Loops - Coordinates parallel researcher agents through iterative planning and synthesis loops.
- Deep Research Execution - Executes multi-agent workflows across papers, web, and code to produce cited briefs or deep dives.
- Bounded Experiment Loops - Executes autonomous bounded experiment loops with benchmark evidence to answer research questions.
- Multi-Agent Orchestration - Orchestrates parallel AI agents to investigate topics and synthesize findings across multiple sources.
- Multi-Agent Research Frameworks - Coordinates parallel researcher agents to investigate topics and synthesize verified findings.
- Cited Brief Generators - Generates concise, citation-backed research briefs from academic papers and web sources.
- Paper and Web Searchers - Queries academic papers and web sources to produce cited research briefs on topics.
- Claim Auditors - Audits research paper claims against actual code implementations to identify mismatches.
- Claim Audits - Audits research paper claims against actual code implementations to identify mismatches.
- Implementation Audits - Compares claims in academic papers against actual code implementations to identify mismatches.
- Replication Plans - Generates step-by-step replication plans with environment selection and compute target configuration.
- Automated Literature Reviewers - Produces structured literature reviews with cited references covering consensus and open questions.
- Multi-Source Research Investigations - Runs multi-agent investigations that search papers, web, and code to produce cited briefs.
- Replication Checkers - Creates replication plans for paper results and runs checks after environment selection.
- Replication Planners - Generates step-by-step plans for reproducing research results with environment selection.
- Scheduled Research Digests - Establishes baselines for research topics with optional schedules for follow-up investigations.
- Research Report Drafting - Produces structured drafts in the style of academic papers from research findings.
- Hub Inspectors - Reads dataset metadata and accesses files from Hugging Face model, dataset, and Space repositories.
- Automated Research Paper Analysis - Structures collected findings and citations into polished, paper-style drafts with inline references.
- Platform-Specific Paper Queries - Queries papers, reads code, and accesses annotations on the AlphaXiv platform.
- Reading Priority Rankers - Scores papers by citation, method, and reproducibility to recommend reading priority.
- Relevance Rankers - Scores academic papers by citation, methodology, and reproducibility metrics for reading priority.
- Training Recipes - Searches papers, datasets, and code to find actionable and ranked ML training recipes.
- Academic Paper Resolvers - Resolves legal full-text access for academic papers from multiple sources.
- Session Context Search - Searches across prior research sessions to recall and index information for reuse.
- Containerized Experiment Executions - Executes replication and benchmark experiments in Docker, Modal, or RunPod containers.
- Research Session Recall - Indexes and searches prior research sessions for reuse and continuity.
Star history
How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
