Scientific & Academic Research
Finding, reading and citing scholarly literature and scientific data. As of 2026-11-21, 374 indexed products match this subcategory (93 with full profiles); 174 were published in the last 90 days, against 78 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, scientific-agent-skills leads, holding 41% of the stars of the 265 products here with their own repository. The most common form is MCP servers (88% of indexed products).
SubcategorySegment label: Lagging the catalogue DER
Segment statistics
Whole catalogue (all 374 indexed products, not only profiled ones). Calculated 2026-11-21.
Lagging the catalogue. Mid-sized for its level, with launches growing more slowly than the catalogue’s. Size is ranked against the other subcategory nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).
Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.194, attention is spread as if across about 5 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is moderately concentrated. Stars measure attention, not usage or quality.
Which product forms serve it
The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 330 | 88.2% | 52 |
| Agent skills | 26 | 7.0% | 26 |
| Infrastructure | 6 | 1.6% | 6 |
| Plugins | 5 | 1.3% | 4 |
| Frameworks | 4 | 1.1% | 4 |
| Rules packs | 2 | 0.53% | 0 |
| Agent projects | 1 | 0.27% | 1 |
4 capabilities
Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.
| Capability | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Paper SearchSearching scholarly databases for papers. | 210 | 42 | 109 | Crowded |
| Scientific ComputingDomain tools for biology, chemistry and math. | 112 | 23 | 44 | Lagging the catalogue |
| Citation ManagementManaging references and bibliographies. | 49 | 23 | 17 | Lagging the catalogue |
| Literature ReviewSummarizing and synthesizing research literature. | 38 | 16 | 12 | Thin |
Top 40 products by GitHub stars
Search the directoryProfiled products only (93 of 374), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | scientific-agent-skillsTurn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard. | Agent skill | K-Dense-AI | 58k | 5d ago | MIT | ||
| 2 | LEANN[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device. | Infrastructure | StarTrail-org | 14k | 1d ago | MIT | ||
| 3 | Firecrawl MCP ServerFirecrawl, the context API for AI agents: search, scrape, interact with the web, plus paper search. | MCP server | firecrawl | 7.9k | 1d ago | MIT | ||
| 4 | claude-scholarSemi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication. | Agent project | Galaxy-Dawn | 6.1k | 1mo ago | MIT | ||
| 5 | Zotero MCPSearch, read, annotate, and add to your Zotero research library, local or web. | MCP server | 54yyyu | 6.0k | 2d ago | MIT | ||
| 6 | open-scienceThe open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux. | Agent skill | aipoch | 5.6k | today | Apache-2.0 | ||
| 7 | exaExa AI web search, deep research, and content extraction. Provides MCP tools and research skills for comprehensive web search, people discovery, company research, academic papers, and more. | Plugin | exa-labs | 5.3k | today | MIT | ||
| 8 | sepiaDe-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136). | Agent skill | Nanako0129 | 3.9k | 18d ago | MIT | ||
| 9 | arxiv-mcp-serverSearch arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP. | MCP server | blazickjp | 3.3k | 7d ago | Apache-2.0 | ||
| 10 | Awesome-REACurated tools, case studies and papers for reverse engineering websites, games, apps, binaries, firmware and protocols. Source-reviewed, English and Chinese. | Agent skill | reacher-z | 3.3k | today | MIT | ||
| 11 | paper-search-mcpMCP, CLI, Skills for searching and downloading academic papers from multiple sources like arXiv, PubMed, bioRxiv, etc. | MCP server | openags | 3.1k | 1mo ago | MIT | ||
| 12 | PaperBananaGenerate academic diagrams and statistical plots from text using multi-agent AI. | MCP server | llmsresearch | 2.5k | 2mo ago | MIT | ||
| 13 | bootcampDealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc. | Infrastructure | milvus-io | 2.5k | 1mo ago | Apache-2.0 | ||
| 14 | AISafetyHotAI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP. | MCP server | wuyoscar | 2.1k | today | — | ||
| 15 | MirobodyLab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key. | MCP server | thetahealth.ai | 1.6k | 1d ago | Apache-2.0 | ||
| 16 | DeepPaperNoteTurn one dense paper into an Obsidian note worth keeping: read the way its field reads it, linked to the papers already in your vault, and aimed at your own research. Agent skills for Claude Code, Codex, Cursor, and any agent that supports skills. | Agent skill | 917Dhj | 1.4k | 2d ago | MIT | ||
| 17 | zotero-mcpIt's a plugin extension in Zotero. Zotero MCP Plugin enables integration between AI assistants and Zotero through MCP. Zotero MCP Plugin 是一个 Zotero 插件,通过 MCP协议实现 AI 助手与 Zotero深度集成。插件支持文献检索、元 数据管理、全文分析和智能问答等功能,让 Claude、ChatGPT 等 AI 工具能够直接访问和操作您的文献库。 | MCP server | cookjohn | 1.3k | 9d ago | MIT | ||
| 18 | Light-ScienceA research workflow skill pack connecting literature, experiments, figures, writing, memory and project coordination. | Agent skill | Light0305 | 1.1k | 13d ago | MIT | ||
| 19 | Deepscient让 AI 与人类一起攻克真正的科学难题 —— 12 阶段 55 门 · 36 工具 · 98 条技能 · 证据链与可复现 | Agent skill | yzlin286-wq | 986 | 27d ago | MIT | ||
| 20 | PaperOrchestraAn automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs. | Agent skill | Ar9av | 767 | 17d ago | — | ||
| 21 | ai-research-skillsUniversal SKILL.md catalog for research workflows: literature review, research design, project memory, manuscript writing, and cross-agent delegation for Claude Code, Codex, Gemini, Cursor, OpenClaw, and generic AI clients. | Agent skill | WenyuChiou | 687 | 2d ago | MIT | ||
| 22 | biomcpBioMCP: Biomedical Model Context Protocol | MCP server | genomoncology | 683 | 11d ago | MIT | ||
| 23 | AAAI-2024-PapersAAAI 2024 Papers: Explore a comprehensive collection of innovative research papers presented at one of the premier artificial intelligence conferences. Seamlessly integrate code implementations for better understanding. ⭐ experience the forefront of progress in artificial intelligence with this repository! | Framework | DmitryRyumin | 589 | 1y ago | MIT | ||
| 24 | DocsAgent — Zotero, Obsidian & Apple Notes MCP ServerInstant, private access to your knowledge base: Zotero, Obsidian, Apple Notes (macOS). | MCP server | docsagent | 580 | 5d ago | — | ||
| 25 | ArXivChatGuruUse ArXiv ChatGuru to talk to research papers. This app uses LangChain, OpenAI, Streamlit, and Redis as a vector database/semantic cache. | Infrastructure | redis-developer | 560 | 8mo ago | MIT | ||
| 26 | AegisRuntime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes. | Infrastructure | Justin0504 | 524 | 21d ago | MIT | ||
| 27 | PRO-LONGProgrammatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064) | Infrastructure | alexisfox7 | 465 | 18d ago | MIT | ||
| 28 | SciAgent-Skills197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon. | Agent skill | jaechang-hits | 395 | 5d ago | — | ||
| 29 | medsci-skillsAgent Skills for medical research — literature search, reporting-guideline & citation checks, statistics, publication figures, submission. Works with Claude Code, Codex, Cursor & GitHub Copilot. Built by a physician-researcher, tested on real publications. MIT. | Agent skill | Aperivue | 393 | today | MIT | ||
| 30 | olcliOverleaf projects from an MCP client: files, compile and PDF, diff, comments and tracked changes | MCP server | aloth | 270 | 2d ago | MIT | ||
| 31 | firecrawl-claude-pluginFirecrawl plugin for Claude Code: search the live web, developer docs, government sources and research papers, run structured data providers, and scrape a page into clean Markdown. Firecrawl is the context API for AI agents. | Agent skill | firecrawl | 264 | 2d ago | MIT | ||
| 32 | research-starter-skills面向科研新手的 Codex 科研协作技能集:选题、文献检索与阅读、论文写作、自然润色、审稿返修和可编辑学术汇报。结合 Research-Starter-Kit 原创教程,用 1 个总入口与 6 个专业模块推进研究。 Research training, writing & editable presentations for Codex. | Agent skill | YCC-Lover | 263 | 21d ago | — | ||
| 33 | Misaka-AgentA multi-agent research system for the humanities and social sciences. | Framework | Luciole-Studio | 257 | 2d ago | Apache-2.0 | ||
| 34 | scholar-search-mcpAn MCP server for academic paper search that integrates with AI assistants (e.g., Claude Code, Cursor), enabling them to search and retrieve academic paper metadata. | MCP server | Silung | 246 | 6mo ago | MIT | ||
| 35 | ZotSeekAI semantic search for Zotero, with a built-in MCP server for AI agents (Claude Code, Codex). Find papers by meaning. 100% local and private. | MCP server | introfini | 242 | 6d ago | — | ||
| 36 | design-harnessFeed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas makes it readable. An Agent Skill for Claude Code & any SKILL.md-compatible agent. | Plugin | tigerless-labs | 236 | 2mo ago | — | ||
| 37 | paper-preflightChecks every LaTeX reference against Crossref, dblp, arXiv, DataCite, PubMed and OpenAlex. No LLM. | MCP server | amos689 | 218 | 1mo ago | MIT | ||
| 38 | Awesome-Gaussian-Skills1000+ arXiv-verified 3DGS methods · 15 AI agent skills · MCP server (34 tools) · open ebook — the AI-native entry to 3D Gaussian Splatting research | MCP server | jaccen | 190 | 1d ago | Apache-2.0 | ||
| 39 | pubmed-mcp-serverSearch PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms. | MCP server | cyanheads | 169 | 8d ago | Apache-2.0 | ||
| 40 | Zotero MCPSearch your Zotero library, retrieve item metadata, and read full text from AI assistants. | MCP server | kujenga | 162 | 3mo ago | MIT |
Most common integrations
Third-party services named by products in this node, whole catalogue.
Launches per month
New Scientific & Academic Research products per monthSRC
Whole catalogue, by publication month, 2025-04 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2025-04 | 2 |
| 2025-05 | 1 |
| 2025-06 | 1 |
| 2025-08 | 1 |
| 2025-09 | 7 |
| 2025-10 | 6 |
| 2025-12 | 2 |
| 2026-01 | 5 |
| 2026-02 | 15 |
| 2026-03 | 23 |
| 2026-04 | 26 |
| 2026-05 | 20 |
| 2026-06 | 35 |
| 2026-07 | 25 |
| 2026-08 | 19 |
| 2026-09 | 45 |
| 2026-10 | 70 |
| 2026-11 | 52 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
No scored opportunity here
Capability gaps are only scored inside subcategories with at least 20 indexed products, and only the top 80 are kept. None falls under this node.
Limits of these numbers
- Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
- About half of the catalogue matches no node at all, so absolute counts understate every category.
- Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
- Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.
Page data last updated .