1,136 projects whose own agent configuration covers research. These are not mods to install — they are how the maintainers of these repositories tell an agent what to do, and what to avoid.
All projects Building agents8,442Claude Code6,875Data and AI3,584Git and workflow3,574Backend and APIs3,550Languages3,468Planning3,315Code review2,876Testing2,653DevOps and cloud2,462Writing and docs2,461Memory and context2,373
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| yaojingang/geo-citation-lab GEO experiment data reports and a curated GEO/AEO/AI search paper library. | 737 | Codex, OpenCode | 1 | 1,261 tok |
| nominal-io/instro instro.nominal.io An open-source library for hardware test instrumentation | 729 | Claude Code, Codex, GitHub Copilot, OpenCode | 7 | 8,057 tok |
| PKU-YuanGroup/OpenAI4S arxiv.org A Claude Science replica using the 9.9-yuan Doubao API | 662 | Claude Code, Codex, OpenCode | 2 | 8,229 tok |
| chainbase-labs/Agentkey agentkey.app Connect your AI agent to the world — Web search, Social media, Crypto & On-chain data. One | 657 | Codex, OpenCode | 1 | 3,953 tok |
| NanmiCoder/NewsCrawler Multi-platform News & Content Crawler Suite | Supports WeChat Official Accounts, Twitter, | 638 | Claude Code, Codex, OpenCode | 3 | 4,430 tok |
| xiao24bei/xiaobei-skill xiaobeiai.top Xiaobei's open-source Codex Skills collection for graduate study: AI + research workflows | 609 | Codex, OpenCode | 1 | 190 tok |
| ZimoLiao/scholaraio zimoliao.github.io Scholar All-In-One: A research infrastructure for AI agents | 584 | Claude Code, Codex, GitHub Copilot, Cursor, OpenCode, Windsurf | 49 | 2,699 tok |
| microsoft/DebugMCP Gift your VS Code agent a real debugger: breakpoints, stepping, inspection. | 579 | Codex, OpenCode | 1 | 970 tok |
| Lumen-Labs/brainapi2 brainapi.lumen-labs.ai BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data in | 549 | Claude Code, Codex, OpenCode | 2 | 53 tok |
| chrisdoc/hevy-mcp hevy-mcp.dev Manage your Hevy workouts, routines, folders, and exercise templates. Create and update se | 533 | Claude Code, Codex, OpenCode | 2 | 2,200 tok |
| Muvon/octocode octomind.run Structural code intelligence for AI agents — semantic search, knowledge graphs, and a buil | 522 | Codex, OpenCode | 1 | 1,909 tok |
| Piebald-AI/gemini-cli-desktop Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search ac | 519 | Claude Code, Codex, OpenCode | 2 | 8,851 tok |
| WILLOSCAR/research-units-pipeline-skills Research pipelines as semantic execution units: each skill declares inputs/outputs, accept | 517 | Codex, OpenCode | 1 | 423 tok |
| yogsoth-ai/de-anthropocentric-research-engine Give an AI a research direction: it runs literature synthesis, gap validation, hypothesis | 510 | Codex, OpenCode | 1 | 278 tok |
| claude-world/notebooklm-skill youtu.be NotebookLM does the research, Claude writes the content. Research → Synthesis → Content Cr | 492 | Codex, GitHub Copilot, OpenCode | 2 | 990 tok |
| lllllllama/RigorPilot-Skills README-first research reproduction skills with bounded execution, auditable evidence, and | 486 | Codex, OpenCode | 1 | 831 tok |
| Episkey-G/GrokSearch-rs Rust MCP server for Grok web search and Tavily-backed source retrieval | 458 | Codex, OpenCode | 1 | 758 tok |
| MinghuiChen43/awesome-deep-phenomena A curated list of papers of interesting empirical study and insight on deep learning. Cont | 412 | Codex, OpenCode | 1 | 1,891 tok |
| elliottdehn/open-jobs ~3M live jobs from 36 ATS, enriched with LLM-extracted fields + embeddings, released CC0. | 399 | Claude Code, Codex, OpenCode | 2 | 5,892 tok |
| MinghuiChen43/awesome-trustworthy-deep-learning A curated list of trustworthy deep learning papers. Continually updating... | 395 | Codex, OpenCode | 1 | 1,925 tok |
| djfksjd/ir-search 🇰🇷 Korean government support program comprehensive research agent Skill [supports Claude | 393 | Claude Code, Codex, OpenCode | 3 | 588 tok |
| BlockRunAI/blockrun-mcp npmjs.com Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x | 389 | Claude Code, Codex, OpenCode | 2 | 564 tok |
| jaechang-hits/SciAgent-Skills omicshorizon.ai 197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% ac | 384 | Claude Code, Codex, OpenCode | 2 | 7,521 tok |
| monarchjuno/tradingcodex discord.gg Turn Codex into your investment workflow team | 380 | Codex, OpenCode | 1 | 2,165 tok |
| K-Dense-AI/science-superpowers k-dense.ai Composable computational-science methodology skills for AI research agents — pre-registrat | 371 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 688 tok |
| modelstudioai/cli bailian.console.aliyun.com Official Model Studio CLI（Alibaba Cloud Bailian CLI）built for AI Agent frameworks, exposin | 369 | Claude Code, Codex, OpenCode | 2 | 3,889 tok |
| imsai-sh/awesome-deepseek-harness-plugins deepseek1024.com DeepSeek Harness plugin store, marketplace and hub — 11,000+ dsh plugins with search, rank | 365 | Claude Code, Codex, OpenCode | 2 | 1,060 tok |
| Kronuz/Xapiand kronuz.github.io Xapiand: A RESTful Search Engine | 363 | Codex, OpenCode | 1 | 2,786 tok |
| jahala/tilth jahala.github.io Smart code reading for humans and AI agents. Definitions, callers, dependencies and functi | 358 | Claude Code, Codex, OpenCode | 2 | 2,459 tok |
| ktwu01/benchmark-radar benchmark-radar.org Track 42,331+ AI benchmark, eval, dataset, and data-quality records from 40 public sources | 355 | Codex, OpenCode | 1 | 1,973 tok |
| drivelineresearch/autoresearch-claude-code Autonomous experiment loop skill for Claude Code — port of pi-autoresearch | 348 | Claude Code, Codex, OpenCode | 2 | 555 tok |
| 7df-lab/devo devo.7df.ai A self-improving agent. Tested on DeepSeek, Qwen, Kimi, GLM models. Supports MCP, Skills. | 345 | Codex, OpenCode | 1 | 1,652 tok |
| hpi-swa/trufflesqueak A Squeak/Smalltalk VM and Polyglot Programming Environment for the GraalVM. | 319 | Codex, OpenCode | 1 | 1,043 tok |
| edinetdb/dexter-jp edinetdb.jp Autonomous research AI agent for Japanese stocks | AI agent for deep financial research on | 317 | Codex, OpenCode | 1 | 2,004 tok |
| geolens-io/geolens getgeolens.com Self-hosted geospatial data catalog with semantic search (pgvector), OGC/STAC APIs, and ma | 291 | Claude Code, Codex, OpenCode | 2 | 4,535 tok |
| maxwell2732/codex-stata-for-economists A Codex Stata pipeline for Economists by 朱晨 | Genetic Social Science Research. | 285 | Claude Code, Codex, OpenCode | 33 | 5,263 tok |
| byteseek/Mira Agent-native investment research workspace for evidence-tracked, refreshable investment th | 282 | Claude Code, Codex, OpenCode | 2 | 1,883 tok |
| s-stefanov/actual-mcp Model Context Protocol for Actual Budget API | 279 | Claude Code, Codex, OpenCode | 2 | 1,715 tok |
| haolange/InfinityRenderPipeline Graphics Research for Unity Scriptable Render Pipeline. | 273 | Codex, OpenCode | 1 | 9,682 tok |
| NomaDamas/katok Agents also have the right to view and search KakaoTalk—from BM25 to Vector Search | 268 | Claude Code, Codex, OpenCode | 2 | 835 tok |
| xiangyugongzuoliu/awesome-rss-feeds-list xiangyugongzuoliu.com 🌐 The most comprehensive collection of RSS feeds on the entire web | 262 | Claude Code, Codex, OpenCode | 2 | 264 tok |
| Dictation354/paper-fetch-skill Fetch papers as agent-ready markdown — DOI/URL/title in, structured full text out. CLI · M | 257 | Codex, OpenCode | 1 | 965 tok |
| NanmiCoder/skills-agent-proto A Skills Agent built with LangChain 1.0, demonstrating the underlying principles of Anthro | 256 | Claude Code, Codex, OpenCode | 3 | 1,389 tok |
| Ariestar/sivtr sivtr.pages.dev A unified agent memory workspace for human and agent | A unified agent memory workspace | 255 | Claude Code, Codex, OpenCode | 5 | 6,045 tok |
| arc-mcp/arc-1 docs.arc-1-mcp.com | 252 | Claude Code, Codex, OpenCode | 12 | 15,865 tok |
| Yeachan-Heo/My-Jogyo Your one-click scientific research lab for Opencode - with seamless .ipynb and REPL integr | 243 | Codex, OpenCode | 1 | 12,003 tok |
| barretlee/agent-pulse barretlee.github.io Evidence-backed AI industry intelligence — trends, source updates, daily data refreshes, a | 239 | Codex, OpenCode | 1 | 2,533 tok |
| ProjectDXAI/labrat dxrg.ai Autonomous multi-branch research lab. Branches compete for compute budget. The system conv | 237 | Claude Code, Codex, OpenCode | 3 | 1,280 tok |
| zebbern/claude-code-discord A Discord bot that brings Claude Code to your channels so you can chat, run shell/git, and | 234 | Codex, OpenCode | 1 | 1,914 tok |
| microsoft/P.808 This is an open-source implementation of the ITU P.808 standard for "Subjective evaluation | 232 | Claude Code, Codex, GitHub Copilot, OpenCode | 6 | 1,712 tok |