AGENTS.md is the repo-level contract for agents working in this repository. Pi subagent behavior does not live here. The source of truth for bundled Pi subagents is .feynman/agents/*.md, which the runtime syncs into the Pi agent directory. If you need to change how researcher, reviewer, writer, or verifier behave, edit the corresponding file in .feynman/agents/ instead of duplicating those prompts here. Feynman ships four bundled research subagents: They are defined in .feynman/agents/ and invoked via the Pi subagent tool. Keep…
Surging+2 new adopters in 4 weeks
2 projects use a version of this
10k33d agoReviewMountCreate a free account to mount
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.
Surging+2 new adopters in 4 weeks
4 projects use a version of this
10k33d agoReviewMountCreate a free account to mount
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.
Surging+2 new adopters in 4 weeks
95 projects use a version of this
10k33d agoReviewMountCreate a free account to mount
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.
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.
Surging+2 new adopters in 4 weeks
53 projects use a version of this
10k33d agoReviewMountCreate a free account to mount
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.
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.
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.
Surging+2 new adopters in 4 weeks
2 projects use a version of this
10k33d agoReviewMountCreate a free account to mount
Compare a paper's claims against its public codebase. Use when the user asks to audit a paper, check code-claim consistency, verify reproducibility of a specific paper, or find mismatches between a paper and its implementation.
Surging+2 new adopters in 4 weeks
3 projects use a version of this
10k33d agoReviewMountCreate a free account to mount
Turn research findings into a polished paper-style draft with sections, equations, and citations. Use when the user asks to write a paper, draft a report, write up findings, or produce a technical document from collected research.
Surging+2 new adopters in 4 weeks
33 projects use a version of this
10k33d agoReviewMountCreate a free account to mount
Read, extract, and cross-check content across scientific PDFs. Use when a task needs methods, figures, tables, citations, accessions, or claims from multiple places in one or more papers.
Surging+2 new adopters in 4 weeks
7 projects use a version of this
10k33d agoReviewMountCreate a free account to mount
Render Markdown or LaTeX research artifacts to HTML or PDF with pandoc. Use when the user wants to review a written artifact, export a report, or view a rendered document.
Surging+2 new adopters in 4 weeks
15 projects use a version of this
10k33d agoReviewMountCreate a free account to mount
Plan a replication of a paper, claim, or benchmark, and execute only after an explicit environment choice. Use when the user asks to replicate results, reproduce an experiment, verify a claim empirically, or build a replication package.
Surging+2 new adopters in 4 weeks
2 projects use a version of this
10k33d agoReviewMountCreate a free account to mount
Run a tough but constructive internal research critique of an AI research artifact. Use when the user asks for a review, critique, feedback on a paper or draft, or wants to identify weaknesses before submission.
Write a durable session log capturing completed work, findings, open questions, and next steps. Use when the user asks to log progress, save session notes, write up what was done, or create a research diary entry.
Surging+2 new adopters in 4 weeks
21 projects use a version of this
10k33d agoReviewMountCreate a free account to mount
Search prior Feynman session transcripts on disk. Use when the user asks about earlier research sessions, past findings, or wants to resume a prior session.
Surging+2 new adopters in 4 weeks
12 projects use a version of this
10k33d agoReviewMountCreate a free account to mount
Compare multiple sources on a topic and produce a grounded comparison matrix. Use when the user asks to compare papers, tools, approaches, frameworks, or claims across multiple sources.
Surging+2 new adopters in 4 weeks
2 projects use a version of this
10k33d agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
advaitpaliwalAGENTS.md