{"projects":[{"name":"OpenClaw","description":"The core platform. Personal AI assistant on your own devices. 25+ messaging channels (WhatsApp, Telegram, Slack, Discord, Signal, iMessage, Teams, Matrix, Feishu, LINE, WeChat, QQ). Voice on macOS/iOS/Android. Live Canvas rendering. Gateway control plane. 358K+ stars.","github":"https://github.com/openclaw/openclaw","repo":"openclaw/openclaw","language":"TypeScript","static_stars":"352.9K","tags":["ai-assistant","multi-platform","voice","canvas"],"category":"core","homepage":null,"paper":null},{"name":"NanoBot","description":"Ultra-lightweight personal AI agent — 99% fewer lines of code than OpenClaw. v0.1.5: Dream skill discovery, mid-turn follow-up injection, WebSocket channel, context auto-compact, notebook editing, multiple MCP servers. Supports Feishu streaming, QQ, WeCom, Kagi web search. From HKUDS (ClawTeam team). 39K+ stars.","github":"https://github.com/HKUDS/nanobot","repo":"HKUDS/nanobot","language":"Python","static_stars":"38.7K","tags":["lightweight","multi-model","MCP","sub-agents"],"category":"core","homepage":null,"paper":null},{"name":"PicoClaw","description":"Tiny, fast, and deployable anywhere. Ultra-efficient AI assistant written in Go by Sipeed. Designed for edge devices and resource-constrained environments. Inspired by NanoBot.","github":"https://github.com/sipeed/picoclaw","repo":"sipeed/picoclaw","language":"Go","static_stars":"27.9K","tags":["edge","IoT","RISC-V","tiny"],"category":"core","homepage":"https://picoclaw.io","paper":null},{"name":"MicroClaw","description":"Agentic AI assistant built with Rust. Runs on <1MB RAM targeting $2-5 MCU hardware like ESP32. The smallest member of the Claw family for sensor-level embedded AI.","github":"https://github.com/microclaw/microclaw","repo":"microclaw/microclaw","language":"Rust","static_stars":"636","tags":["embedded","MCU","ESP32","rust"],"category":"core","homepage":null,"paper":null},{"name":"Clawith","description":"OpenClaw for Teams. Multi-agent collaboration with persistent identity, long-term memory, and autonomous 'Aware' consciousness system. 6 trigger types: cron, once, interval, poll, on_message, webhook.","github":"https://github.com/dataelement/Clawith","repo":"dataelement/Clawith","language":"Python","static_stars":"3K","tags":["teams","multi-agent","awareness","FastAPI"],"category":"team","homepage":null,"paper":null},{"name":"MetaClaw","description":"Self-learning agent that evolves from every conversation. LoRA-based continual learning + reinforcement learning, no GPU cluster needed. Supports OpenClaw, NanoBot, PicoClaw backends.","github":"https://github.com/aiming-lab/MetaClaw","repo":"aiming-lab/MetaClaw","language":"Python","static_stars":"3.5K","tags":["meta-learning","LoRA","self-evolving","RL"],"category":"team","homepage":null,"paper":"https://arxiv.org/abs/2603.17187"},{"name":"EvoScientist","description":"Self-evolving multi-agent AI research system. Harness Vibe Research — 6 sub-agents (plan, research, code, debug, analyze, write) that evolve their capabilities over time. Built on DeepAgents framework. PyPI installable. Multi-platform: CLI, Telegram, Slack, WeChat. Apache 2.0 license.","github":"https://github.com/EvoScientist/EvoScientist","repo":"EvoScientist/EvoScientist","language":"Python","static_stars":"2.8K","tags":["AI4Science","multi-agent","auto-research","award-winning"],"category":"science","homepage":"https://EvoScientist.ai","paper":"https://arxiv.org/abs/2603.08127"},{"name":"MedgeClaw","description":"AI research assistant for biomedicine built on Claude Code with 140 K-Dense scientific skills. Real-time research dashboard, RStudio (:8787), JupyterLab (:8888), and Feishu rich card output.","github":"https://github.com/xjtulyc/MedgeClaw","repo":"xjtulyc/MedgeClaw","language":"TeX","static_stars":"856","tags":["biomedicine","RNA-seq","drug-discovery","clinical"],"category":"science","homepage":null,"paper":null},{"name":"OmicsClaw","description":"Local-first cross-session AI assistant for life science researchers. 63 built-in skills across 6 omics domains (spatial transcriptomics, scRNA-seq, bulk RNA-seq, genomics, proteomics, metabolomics). Multi-Provider (Anthropic/OpenAI/DeepSeek/local LLM), Multi-Channel (CLI + Feishu/WeChat/Telegram sync), MCP + dynamic GitHub skill install. Persistent memory. 100% local — no data leaves your machine.","github":"https://github.com/TianGzlab/OmicsClaw","repo":"TianGzlab/OmicsClaw","language":"Python","static_stars":"114","tags":["6-omics","63-skills","multi-provider","local-first","cross-session-memory"],"category":"science","homepage":null,"paper":null},{"name":"LabClaw","description":"Operating layer for LabOS — Stanford-Princeton AI Co-Scientists project. Automated scientific co-discovery workflows for laboratory research.","github":"https://github.com/wu-yc/LabClaw","repo":"wu-yc/LabClaw","language":"Python","static_stars":"945","tags":["Stanford","Princeton","lab-automation","co-discovery"],"category":"science","homepage":null,"paper":null},{"name":"MedClaw (zteyesreal)","description":"Early-stage medical AI project exploring agent-based approaches for clinical decision support and medical data analysis.","github":"https://github.com/zteyesreal/medclaw","repo":"zteyesreal/medclaw","language":"Python","static_stars":"60","tags":["medical","clinical","early-stage"],"category":"science","homepage":null,"paper":null},{"name":"OpenMAIC","description":"Open Multi-Agent Interactive Classroom by Tsinghua University. One-click immersive AI classroom with multi-agent learning experience. Published in JCST'26. Live demo at open.maic.chat. Built with Next.js 16 + React 19 + LangGraph. Vercel one-click deploy. OpenClaw integration. 15K+ stars.","github":"https://github.com/THU-MAIC/OpenMAIC","repo":"THU-MAIC/OpenMAIC","language":"TypeScript","static_stars":"14.7K","tags":["Tsinghua","classroom","multi-agent","PBL"],"category":"education","homepage":"https://open.maic.chat","paper":"https://doi.org/10.1007/s11390-025-6000-0"},{"name":"ZeroClaw","description":"Fast, small, and fully autonomous AI assistant infrastructure. Deploy anywhere, swap anything. Written in Rust with extreme performance focus — the infrastructure layer for self-hosted AI agents.","github":"https://github.com/zeroclaw-labs/zeroclaw","repo":"zeroclaw-labs/zeroclaw","language":"Rust","static_stars":"29.8K","tags":["infrastructure","autonomous","deploy-anywhere","Rust"],"category":"core","homepage":null,"paper":null},{"name":"NanoClaw","description":"Lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail. Built on Anthropic Agents SDK with memory and scheduled jobs.","github":"https://github.com/qwibitai/nanoclaw","repo":"qwibitai/nanoclaw","language":"TypeScript","static_stars":"27K","tags":["container","secure","Anthropic-SDK","lightweight"],"category":"core","homepage":null,"paper":null},{"name":"ClawX","description":"Desktop app providing a graphical interface for OpenClaw AI agents. Turns CLI-based AI orchestration into a visual desktop experience without using the terminal.","github":"https://github.com/ValueCell-ai/ClawX","repo":"ValueCell-ai/ClawX","language":"TypeScript","static_stars":"6.3K","tags":["desktop","GUI","agent-orchestration","visual"],"category":"team","homepage":null,"paper":null},{"name":"ClawBio","description":"The first bioinformatics-native AI agent skill library. Local-first, reproducible, built on OpenClaw. Covers genomics, population genetics, and equity-focused bioinformatics workflows.","github":"https://github.com/ClawBio/ClawBio","repo":"ClawBio/ClawBio","language":"Python","static_stars":"678","tags":["bioinformatics","genomics","local-first","reproducible"],"category":"science","homepage":null,"paper":null},{"name":"BioClaw","description":"AI-powered bioinformatics research assistant built on OpenClaw. Integrates PubMed literature search and PyMOL molecular visualization for streamlined biological research workflows.","github":"https://github.com/Runchuan-BU/BioClaw","repo":"Runchuan-BU/BioClaw","language":"TypeScript","static_stars":"323","tags":["bioinformatics","PubMed","PyMOL","research-assistant"],"category":"science","homepage":"https://iveGotMagicBean.github.io/BioClaw-Page/","paper":null},{"name":"EdgeClaw","description":"Edge-Cloud Collaborative AI Agent built on OpenClaw — bringing the Claude Code experience to open source. v2.0 features ClawXMemory (multi-layered structured long-term memory with proactive reasoning) and ClawXRouter (LLM-as-Judge cost-saving router achieving 58% savings). Three-tier privacy (S1 Passthrough / S2 Desensitization / S3 Local), visual Dashboard, zero-config setup. By THUNLP, RUC, OpenBMB.","github":"https://github.com/Openbmb/EdgeClaw","repo":"Openbmb/EdgeClaw","language":"TypeScript","static_stars":"1.2K","tags":["edge-cloud","privacy","memory","cost-saving","Tsinghua","OpenBMB"],"category":"core","homepage":null,"paper":null},{"name":"MolClaw","description":"Light, practical, memory-enabled AI orchestrator for science. Built on NanoClaw. Adds OpenAI/OpenRouter providers, Discord/WhatsApp channels, runtime skills, durable session memory, and real-time agent execution dashboard.","github":"https://github.com/IDEA-XL/MolClaw","repo":"IDEA-XL/MolClaw","language":"TypeScript","static_stars":"19","tags":["molecular","bioinformatics","NanoClaw-fork","dashboard"],"category":"science","homepage":null,"paper":null},{"name":"PopGenAgent","description":"Tool-aware, reproducible, report-oriented AI workflows for population genomics. Template-driven execution with publication-quality figures, full provenance tracking, and cost-aware LLM routing.","github":"https://github.com/ai4nucleome/POPGENAGENT","repo":"ai4nucleome/POPGENAGENT","language":"Python","static_stars":"12","tags":["population-genetics","genomics","reproducible","report-generation"],"category":"bio-omics","homepage":null,"paper":null},{"name":"Bioinfor-Claw","description":"24/7 bioinformatics copilot — 50 specific skills across 10 application scenarios (data access, multi-omics, CRISPR, gene-list, structure, ML, plotting, literature, lab tracking). Dual nature: standalone agent with browser-based chat UI + modular SKILL.md library that plugs into OpenClaw, Claude Code, or any custom agent. Multi-LLM backend (Anthropic, OpenAI, Google, Mistral, MiniMax, OpenAI-compatible).","github":"https://github.com/MDhewei/bioinfor-claw","repo":"MDhewei/bioinfor-claw","language":"HTML","static_stars":"7","tags":["bioinformatics","copilot","skill-library","openclaw","multi-LLM"],"category":"bio-omics","homepage":null,"paper":null},{"name":"RD-Agent","description":"Microsoft R&D automation platform. AI-driven data and model research — automates hypothesis generation, experiment design, and iterative improvement for industrial and scientific R&D.","github":"https://github.com/microsoft/RD-Agent","repo":"microsoft/RD-Agent","language":"Python","static_stars":"12.4K","tags":["Microsoft","R&D-automation","data-driven","industrial"],"category":"general-research","homepage":null,"paper":null},{"name":"AI-Scientist-v2","description":"Workshop-level automated scientific discovery via agentic tree search. By Sakana AI. Autonomously generates research papers through iterative hypothesis testing and experimentation.","github":"https://github.com/SakanaAI/AI-Scientist-v2","repo":"SakanaAI/AI-Scientist-v2","language":"Python","static_stars":"5.3K","tags":["Sakana-AI","paper-generation","agentic-tree-search","autonomous"],"category":"general-research","homepage":null,"paper":null},{"name":"DATAGEN","description":"AI-driven multi-agent research assistant automating hypothesis generation, data analysis, and report writing. Full research pipeline from question to publication-ready report.","github":"https://github.com/starpig1129/DATAGEN","repo":"starpig1129/DATAGEN","language":"Python","static_stars":"1.7K","tags":["hypothesis-generation","data-analysis","report-writing","multi-agent"],"category":"general-research","homepage":null,"paper":null},{"name":"AIAgents4Pharma","description":"Multi-agent platform for pharmaceutical R&D. Covers drug discovery, drug development, and clinical pipeline automation. Built by VirtualPatientEngine.","github":"https://github.com/VirtualPatientEngine/AIAgents4Pharma","repo":"VirtualPatientEngine/AIAgents4Pharma","language":"Python","static_stars":"76","tags":["pharma","drug-discovery","LangGraph","knowledge-graph"],"category":"drug-molecular","homepage":null,"paper":null},{"name":"OpenLens AI","description":"Fully autonomous multimodal research agent. Combines vision and text understanding for scientific discovery. Chinese academic origin with bilingual support.","github":"https://github.com/jarrycyx/openlens-ai","repo":"jarrycyx/openlens-ai","language":"Python","static_stars":"258","tags":["multimodal","autonomous","vision+text","bilingual"],"category":"specialized","homepage":null,"paper":null},{"name":"BioAgents","description":"AI scientist framework for autonomous deep research in biological sciences. Multi-agent system combining literature analysis with data scientist agents for iterative scientific discovery.","github":"https://github.com/bio-xyz/BioAgents","repo":"bio-xyz/BioAgents","language":"TypeScript","static_stars":"124","tags":["biology","literature-analysis","data-science","iterative-discovery"],"category":"specialized","homepage":null,"paper":null},{"name":"ChemGraph","description":"Agentic framework for computational chemistry and materials science workflows. From Argonne National Laboratory (ALCF). Orchestrates chemistry simulation pipelines.","github":"https://github.com/argonne-lcf/ChemGraph","repo":"argonne-lcf/ChemGraph","language":"Python","static_stars":"90","tags":["Argonne","chemistry","materials-science","simulation"],"category":"drug-molecular","homepage":null,"paper":null},{"name":"OpenAGS","description":"Autonomous Generalist Scientist — AI agent targeting all scientific fields. Broad-scope autonomous research from hypothesis to verification.","github":"https://github.com/openags/OpenAGS","repo":"openags/OpenAGS","language":"Python","static_stars":"50","tags":["generalist","autonomous","all-sciences","hypothesis-to-verification"],"category":"general-research","homepage":null,"paper":null},{"name":"Open Co-Scientist","description":"Open-source adaptation of Google DeepMind's AI Co-Scientist. Generates, reviews, ranks, and evolves research hypotheses using multi-agent architecture.","github":"https://github.com/jataware/open-coscientist","repo":"jataware/open-coscientist","language":"Python","static_stars":"17","tags":["Google-Research-inspired","hypothesis-evolution","multi-agent","open-source"],"category":"general-research","homepage":null,"paper":null},{"name":"SR-Scientist","description":"Scientific equation discovery with agentic AI. Published at ICLR 2026. Symbolic regression via AI agents from GAIR Lab (Shanghai Jiao Tong University).","github":"https://github.com/GAIR-NLP/SR-Scientist","repo":"GAIR-NLP/SR-Scientist","language":"Python","static_stars":"36","tags":["ICLR-2026","equation-discovery","symbolic-regression","SJTU"],"category":"specialized","homepage":null,"paper":"https://arxiv.org/abs/2510.11661"},{"name":"CARIBOU","description":"Computational AI Research Interface for Bioinformatics, Omics, and Unifying Agents. Multi-agent bioinformatics system by OpenTechBio.","github":"https://github.com/OpenTechBio/CARIBOU","repo":"OpenTechBio/CARIBOU","language":"Jupyter Notebook","static_stars":"2","tags":["bioinformatics","omics","multi-agent","early-stage"],"category":"bio-omics","homepage":null,"paper":null},{"name":"AI-Researcher","description":"Autonomous scientific innovation system from HKUDS. NeurIPS 2025 paper. End-to-end research automation: literature review, hypothesis generation, experiment design, and paper writing. Production version at novix.science.","github":"https://github.com/HKUDS/AI-Researcher","repo":"HKUDS/AI-Researcher","language":"Python","static_stars":"5.1K","tags":["NeurIPS-2025","autonomous","paper-writing","HKUDS"],"category":"general-research","homepage":"https://novix.science/chat","paper":null},{"name":"AutoBA","description":"An AI agent for fully automated multi-omic analyses. Supports RNA-seq, scRNA-seq, spatial transcriptomics, WGS/WES, and ChIP-seq with automated code repair.","github":"https://github.com/JoshuaChou2018/AutoBA","repo":"JoshuaChou2018/AutoBA","language":"Python","static_stars":"226","tags":["multi-omics","RNA-seq","spatial-transcriptomics","self-debugging"],"category":"bio-omics","homepage":null,"paper":"https://doi.org/10.1002/advs.202407094"},{"name":"BioDiscoveryAgent","description":"LLM-based AI agent for closed-loop design of genetic perturbation experiments. Autonomous reasoning for biological discovery.","github":"https://github.com/snap-stanford/BioDiscoveryAgent","repo":"snap-stanford/BioDiscoveryAgent","language":"Python","static_stars":"102","tags":["genetic-perturbation","experiment-design","Stanford"],"category":"specialized","homepage":null,"paper":null},{"name":"Virtual Lab","description":"A virtual lab of LLM agents for science research. Multi-agent system for nanobody design with principal investigator agent coordination.","github":"https://github.com/zou-group/virtual-lab","repo":"zou-group/virtual-lab","language":"Python","static_stars":"660","tags":["multi-agent","nanobody-design","protein-engineering","Stanford"],"category":"drug-molecular","homepage":null,"paper":null},{"name":"MDCrow","description":"Molecular dynamics simulations with an LLM agent. Automates simulation setup, execution, and analysis using natural language.","github":"https://github.com/ur-whitelab/MDCrow","repo":"ur-whitelab/MDCrow","language":"Python","static_stars":"234","tags":["molecular-dynamics","simulation","computational-chemistry"],"category":"drug-molecular","homepage":null,"paper":null},{"name":"SpatialAgent","description":"An AI agent for spatial biology by Genentech. Processes multimodal spatial genomics data for research insights.","github":"https://github.com/Genentech/SpatialAgent","repo":"Genentech/SpatialAgent","language":"Python","static_stars":"158","tags":["spatial-biology","genomics","multimodal","Genentech"],"category":"bio-omics","homepage":null,"paper":null},{"name":"CRISPR-GPT","description":"LLM agent for CRISPR genome engineering. Assists with guide RNA design, experiment planning, and protocol optimization.","github":"https://github.com/cong-lab/crispr-gpt-pub","repo":"cong-lab/crispr-gpt-pub","language":"Python","static_stars":"156","tags":["CRISPR","gene-editing","guide-RNA"],"category":"bio-omics","homepage":null,"paper":null},{"name":"BioMaster","description":"AI agent system for various bioinformatics tasks with specialized agent coordination. From the same group as POPGENAGENT.","github":"https://github.com/ai4nucleome/BioMaster","repo":"ai4nucleome/BioMaster","language":"Python","static_stars":"91","tags":["bioinformatics","multi-agent","nucleome"],"category":"bio-omics","homepage":null,"paper":null},{"name":"CellVoyager","description":"AI CompBio agent that autonomously analyzes biological data and generates new insights. From Stanford Zou Group. Published in Nature Methods. Specializes in scRNA-seq with self-debugging and hypothesis generation.","github":"https://github.com/zou-group/CellVoyager","repo":"zou-group/CellVoyager","language":"Python","static_stars":"202","tags":["Stanford","Nature Methods","scRNA-seq","autonomous-analysis"],"category":"bio-omics","homepage":null,"paper":"https://www.nature.com/articles/s41592-026-03029-6"},{"name":"GeneClaw","description":"Self-evolving AI agent framework with 5-layer safety gatekeeper. Agents observe failures, propose fixes, and safely apply them. Built on HKUDS/nanobot.","github":"https://github.com/Clawland-AI/Geneclaw","repo":"Clawland-AI/Geneclaw","language":"Python","static_stars":"34","tags":["self-evolving","safety","nanobot-based"],"category":"specialized","homepage":null,"paper":null},{"name":"PythonClaw","description":"OpenClaw reimagined in pure Python. Autonomous AI agent with memory, RAG, skills, web dashboard, voice input, and multi-channel support (Telegram, etc.).","github":"https://github.com/ericwang915/PythonClaw","repo":"ericwang915/PythonClaw","language":"Python","static_stars":"22","tags":["pure-Python","RAG","memory","voice","web-dashboard"],"category":"core","homepage":null,"paper":null},{"name":"AutoResearchClaw","description":"Fully autonomous, self-evolving research framework: from a one-line idea to a conference-level paper. 23-stage pipeline with multi-agent debate, self-healing error correction, citation verification, and hardware-adaptive execution. Compatible with OpenClaw and MetaClaw.","github":"https://github.com/aiming-lab/AutoResearchClaw","repo":"aiming-lab/AutoResearchClaw","language":"Python","static_stars":"10.8K","tags":["idea-to-paper","self-evolving","23-stage","citation-verification","OpenClaw-compatible"],"category":"paper-tools","homepage":null,"paper":null},{"name":"Dr. Claw","description":"AI Research IDE with built-in \"AI Doctors\" assistants. Full research lifecycle: Survey → Ideation → Experiment → Publication → Promotion. 100+ research skills, auto pipeline planning, real-time task tracking, LaTeX rendering, Git integration. PWA-ready.","github":"https://github.com/OpenLAIR/dr-claw","repo":"OpenLAIR/dr-claw","language":"JavaScript","static_stars":"825","tags":["research-IDE","multi-agent","LaTeX","PWA","full-lifecycle"],"category":"specialized","homepage":null,"paper":null},{"name":"ScienceClaw (Zaoqu-Liu)","description":"AI Research Lab That Never Sleeps. 9 agents, 263 skills, 77 databases — from literature to publication, every discipline, zero boundaries. Full research lifecycle automation.","github":"https://github.com/Zaoqu-Liu/ScienceClaw","repo":"Zaoqu-Liu/ScienceClaw","language":"Shell","static_stars":"43","tags":["9-agents","263-skills","77-databases","full-lifecycle","multi-discipline"],"category":"specialized","homepage":null,"paper":null},{"name":"ScienceClaw (TaichuAI)","description":"Personal research assistant built with LangChain DeepAgents and AIO Sandbox. A new architecture beyond OpenClaw, offering stronger security, better transparency, and a more user-friendly experience.","github":"https://github.com/AgentTeam-TaichuAI/ScienceClaw","repo":"AgentTeam-TaichuAI/ScienceClaw","language":"Python","static_stars":"475","tags":["LangChain","DeepAgents","beyond-OpenClaw","security","transparency"],"category":"specialized","homepage":null,"paper":null},{"name":"MedClaw (Paulzhang)","description":"Medical-domain OpenClaw customization. Tailored for clinical and healthcare AI agent workflows. Chinese-language focused.","github":"https://github.com/Paulzhang2023/medclaw","repo":"Paulzhang2023/medclaw","language":"TypeScript","static_stars":"10","tags":["medical","clinical","Chinese","OpenClaw-fork"],"category":"science","homepage":null,"paper":null},{"name":"MedClaw (Suzano)","description":"Universal framework for domain-specific AI agents covering Medical, Legal, Finance, and Sports. Multi-domain architecture with shared agent infrastructure.","github":"https://github.com/suzano-ai/medclaw","repo":"suzano-ai/medclaw","language":"TypeScript","static_stars":"1","tags":["multi-domain","medical","legal","finance"],"category":"general-research","homepage":null,"paper":null},{"name":"ScienceClaw (beita6969)","description":"Self-evolving AI research colleague. 285 skills that grow at runtime — the agent writes new skills based on your usage patterns. 4-layer persistent memory with LanceDB, 1hr+ session timeout, zero-hallucination citation protocol.","github":"https://github.com/beita6969/ScienceClaw","repo":"beita6969/ScienceClaw","language":"TypeScript","static_stars":"567","tags":["self-evolving","persistent-memory","zero-hallucination","28-disciplines"],"category":"specialized","homepage":null,"paper":null},{"name":"SciClaw (drpedapati)","description":"Paired-scientist AI assistant for reproducible research. Lightweight Go runtime, lifecycle hooks, manuscript integration, 12 baseline scientific skills. PicoClaw-compatible. Homebrew installable.","github":"https://github.com/drpedapati/sciclaw","repo":"drpedapati/sciclaw","language":"Go","static_stars":"51","tags":["Go","reproducible","PicoClaw-compatible","Homebrew","paired-scientist"],"category":"specialized","homepage":null,"paper":null},{"name":"SciClaw (nahisaho)","description":"AI research assistant with Docker sandbox agents. Isolated execution environment for safe, reproducible scientific computing workflows.","github":"https://github.com/nahisaho/sciclaw","repo":"nahisaho/sciclaw","language":"TypeScript","static_stars":"1","tags":["Docker","sandbox","TypeScript","isolated-execution"],"category":"specialized","homepage":null,"paper":null},{"name":"ArgusBot","description":"24/7 supervisor Agent for Codex CLI and Claude Code CLI. Keeps agents running, reviewing, and planning until the job is actually done. Useful for overnight experiments and long-running analysis tasks.","github":"https://github.com/waltstephen/ArgusBot","repo":"waltstephen/ArgusBot","language":"Python","static_stars":"294","tags":["supervisor","24/7","overnight","agent-management"],"category":"team","homepage":null,"paper":null},{"name":"ScienceClaw (MIT LAMM)","description":"Open-source AI agent swarm for crowdsourced scientific discovery. 300+ interoperable tools, plannerless ArtifactReactor coordination, DAG lineage tracking. Agents self-coordinate across institutions via Infinite platform (lamm.mit.edu/infinite). Solving real problems: peptide binder design, ceramic discovery, cross-disciplinary pattern recognition. From MIT LAMM Lab (Markus Buehler). Genesis Mission backed.","github":"https://github.com/lamm-mit/scienceclaw","repo":"lamm-mit/scienceclaw","language":"Python","static_stars":"142","tags":["MIT","agent-swarm","Infinite","multi-agent","crowdsourced-discovery"],"category":"specialized","homepage":"https://lamm.mit.edu/infinite","paper":"https://arxiv.org/abs/2603.14312"},{"name":"EurekaClaw","description":"Self-evolving AI research agent by the EurekaClaw team. Autonomous scientific discovery with persistent memory and tool-use capabilities.","github":"https://github.com/EurekaClaw/EurekaClaw","repo":"EurekaClaw/EurekaClaw","language":"Python","static_stars":"660","tags":["self-evolving","autonomous","discovery"],"category":"general-research","homepage":null,"paper":null},{"name":"OpenCLAW Research Platform","description":"Autonomous multi-agent scientific research platform built on OpenClaw. Vision: a network of specialized AI agents for code, papers, and experiments.","github":"https://github.com/Agnuxo1/OpenCLAW-Autonomous-Multi-Agent-Scientific-Research-Platform","repo":"Agnuxo1/OpenCLAW-Autonomous-Multi-Agent-Scientific-Research-Platform","language":"JavaScript","static_stars":"9","tags":["multi-agent","autonomous","scientific-research"],"category":"general-research","homepage":null,"paper":null},{"name":"RS-PaperClaw","description":"Auto-tracks, auto-analyzes, and auto-digests remote sensing papers. Stop reading remote sensing papers manually.","github":"https://github.com/thinson/RS-PaperClaw","repo":"thinson/RS-PaperClaw","language":"Python","static_stars":"46","tags":["remote-sensing","paper-digest","automation"],"category":"paper-tools","homepage":null,"paper":null},{"name":"PaperClaw (AkaliKong)","description":"Agent-orchestrated pipeline that automates the full academic research lifecycle — from arXiv search and relevance scoring to deep reading, code evaluation, and idea synthesis.","github":"https://github.com/AkaliKong/PaperClaw","repo":"AkaliKong/PaperClaw","language":"Python","static_stars":"22","tags":["paper-management","analysis"],"category":"paper-tools","homepage":null,"paper":null},{"name":"paper_claw (PigeonDan1)","description":"Personalized daily research digests from arXiv and beyond. Customizable categories, intelligent classification, and agent-based multilingual summaries via private API.","github":"https://github.com/PigeonDan1/paper_claw","repo":"PigeonDan1/paper_claw","language":"Python","static_stars":"30","tags":["arXiv","daily-digest","multilingual","email"],"category":"paper-tools","homepage":null,"paper":null},{"name":"Research-Claw","description":"Full-stack AI research assistant — \"In the AI era, why can't everyone be a PI?\" Supports extensible skills, literature review, note-taking, experiment tracking, and paper writing end to end. 350+ plugins available.","github":"https://github.com/wentorai/Research-Claw","repo":"wentorai/Research-Claw","language":"TypeScript","static_stars":"614","tags":["full-stack","PI-for-everyone","extensible"],"category":"paper-tools","homepage":null,"paper":null},{"name":"ResearchClaw (ymx10086)","description":"Personal AI assistant built for research. Fast setup, local or cloud, integrates with chat apps. Streamlines literature review, note-taking, experiment tracking, and paper writing end to end.","github":"https://github.com/ymx10086/ResearchClaw","repo":"ymx10086/ResearchClaw","language":"Python","static_stars":"263","tags":["end-to-end","local+cloud","chat-integration"],"category":"paper-tools","homepage":null,"paper":null},{"name":"InnoClaw","description":"A self-hostable AI research workspace with grounded chat, paper study tools, and scientific skill execution — all anchored to your local files.","github":"https://github.com/SpectrAI-Initiative/InnoClaw","repo":"SpectrAI-Initiative/InnoClaw","language":"TypeScript","static_stars":"369","tags":["innovation","SpectrAI"],"category":"general-research","homepage":null,"paper":null},{"name":"CitationClaw","description":"Turning every citation into explainable impact. Citation analysis and impact assessment tool for academic research — tracks citation networks, measures influence, and provides explainable bibliometric insights.","github":"https://github.com/VisionXLab/CitationClaw","repo":"VisionXLab/CitationClaw","language":"Python","static_stars":"302","tags":["citation-analysis","impact","explainable"],"category":"paper-tools","homepage":null,"paper":null},{"name":"PaperClaw (guhaohao0991)","description":"OpenClaw skill for paper search-review-critique expert-agent. Generates research workflows for specific topics (demo: Scientific ML and 3D geometry).","github":"https://github.com/guhaohao0991/PaperClaw","repo":"guhaohao0991/PaperClaw","language":"Python","static_stars":"200","tags":["paper-review","expert-agent","SciML"],"category":"paper-tools","homepage":null,"paper":null},{"name":"ClawPhD","description":"Agent that turns academic papers into publication-ready diagrams, posters, videos, and more. Visual research communication tool — automates the creation of conference materials from your manuscripts.","github":"https://github.com/ZhihaoAIRobotic/ClawPhD","repo":"ZhihaoAIRobotic/ClawPhD","language":"Python","static_stars":"150","tags":["diagrams","posters","videos","visualization"],"category":"paper-tools","homepage":null,"paper":null},{"name":"PaperClaw (meowscles69) ☠️","description":"[REMOVED] GitHub account deleted. Was: 27 OpenClaw skills for academic research teams — literature reviews, hypothesis versioning, grant writing, lab knowledge handoffs. 141 stars at time of removal.","github":"https://github.com/meowscles69/PaperClaw","repo":"meowscles69/PaperClaw","language":"Python","static_stars":"141","tags":["removed","account-deleted"],"category":"paper-tools","homepage":null,"paper":null},{"name":"PaperClaw (hurtjan)","description":"Transform your PDF paper library into a cross-referenced, queryable citation graph database. AI agents extract metadata, citations, and context from PDFs, then fuzzy-match across papers. Dual environment: Main (ingest) + Query (Haiku-powered, read-only). 41 commits, actively developed.","github":"https://github.com/hurtjan/PaperClaw","repo":"hurtjan/PaperClaw","language":"Python","static_stars":"3","tags":["citation-graph","PDF-ingestion","literature-database","Claude-Code"],"category":"paper-tools","homepage":null,"paper":null},{"name":"paperclaw (cocoafun)","description":"PaperClaw variant with 51 commits. TypeScript implementation.","github":"https://github.com/cocoafun/paperclaw","repo":"cocoafun/paperclaw","language":"TypeScript","static_stars":"2","tags":["TypeScript","paper-tools"],"category":"paper-tools","homepage":null,"paper":null},{"name":"DrClaw (InternScience)","description":"A 7x24 AI research team for academics with 244 skills and 13 agent templates, designed to eliminate repetitive lab work so researchers can focus on thinking.","github":"https://github.com/InternScience/DrClaw","repo":"InternScience/DrClaw","language":"Python","static_stars":"157","tags":["InternScience"],"category":"specialized","homepage":null,"paper":null},{"name":"DrugClaw (QSong)","description":"Agentic RAG for drug intelligence: 57 skills, 15 task categories — DTI, ADR, DDI, pharmacogenomics, repurposing. Powered by LangGraph.","github":"https://github.com/QSong-github/DrugClaw","repo":"QSong-github/DrugClaw","language":"Python","static_stars":"127","tags":["57-skills","LangGraph","DTI","drug-repurposing"],"category":"drug-molecular","homepage":null,"paper":null},{"name":"DrugClaw (DrugClaw)","description":"AI Research Assistant for Accelerated Drug Discovery. Built with Rust for high performance. Covers compound screening, ADMET prediction, and lead optimization workflows.","github":"https://github.com/DrugClaw/DrugClaw","repo":"DrugClaw/DrugClaw","language":"Rust","static_stars":"50","tags":["Rust","drug-discovery","performance"],"category":"drug-molecular","homepage":null,"paper":null},{"name":"ResearchClaw (Noietch)","description":"Standalone Electron desktop app combining AI-powered paper management, interactive reading notes, and research idea generation — no browser or server required.","github":"https://github.com/Noietch/ResearchClaw","repo":"Noietch/ResearchClaw","language":"TypeScript","static_stars":"61","tags":["desktop-app","TypeScript"],"category":"paper-tools","homepage":null,"paper":null},{"name":"PaperClaw (0xMerl99)","description":"Production-ready library of 27 OpenClaw skills for research teams — literature management, synthesis, collaboration, manuscript output, and tracking workflows.","github":"https://github.com/0xMerl99/PaperClaw","repo":"0xMerl99/PaperClaw","language":"Python","static_stars":"42","tags":["paper-management"],"category":"paper-tools","homepage":null,"paper":null},{"name":"research-claw (nanoAgentTeam)","description":"Self-hosted AI assistant for academic research — manages papers, searches literature, tracks deadlines.","github":"https://github.com/nanoAgentTeam/research-claw","repo":"nanoAgentTeam/research-claw","language":"Python","static_stars":"80","tags":["self-hosted","deadlines"],"category":"paper-tools","homepage":null,"paper":null},{"name":"OpenLife","description":"Claw-like Agent for bioinformatics research. Lightweight, Python-based assistant for computational biology workflows.","github":"https://github.com/AndyZhuang/OpenLife","repo":"AndyZhuang/OpenLife","language":"Python","static_stars":"23","tags":["bioinformatics","claw-like"],"category":"bio-omics","homepage":null,"paper":null},{"name":"MatClaw","description":"Open materials-science agent that turns natural-language tasks into reproducible simulation workflows.","github":"https://github.com/DingyangLyu/MatClaw","repo":"DingyangLyu/MatClaw","language":"TypeScript","static_stars":"33","tags":["materials-science","simulation"],"category":"specialized","homepage":null,"paper":null},{"name":"PaperClaw (1692775560)","description":"High-agency AI automation for academic researchers. Three-layer architecture: LLM decision engine, skill execution layer, and memory knowledge management.","github":"https://github.com/1692775560/PaperClaw","repo":"1692775560/PaperClaw","language":"Python","static_stars":"45","tags":["paper-analysis"],"category":"paper-tools","homepage":null,"paper":null},{"name":"ChemClaw","description":"Curated skills package for chemistry-focused AI workflows. Installable modularly via npx with stable and experimental skill tiers.","github":"https://github.com/AI4Chem/ChemClaw","repo":"AI4Chem/ChemClaw","language":"Python","static_stars":"32","tags":["chemistry","AI4Chem"],"category":"drug-molecular","homepage":null,"paper":null},{"name":"Prismer","description":"Open-source alternative to OpenAI's Prism. Unified platform for AI-powered paper reading, learning, and research knowledge management.","github":"https://github.com/Prismer-AI/Prismer","repo":"Prismer-AI/Prismer","language":"TypeScript","static_stars":"893","tags":["open-source","paper-reading","knowledge-management","Prism-alternative"],"category":"general-research","homepage":null,"paper":null},{"name":"IronClaw","description":"Rust implementation of OpenClaw focused on privacy and security. Memory-safe architecture with Rust's ownership model, built by NEAR AI. Ideal for sensitive research environments requiring data isolation and high performance.","github":"https://github.com/nearai/ironclaw","repo":"nearai/ironclaw","language":"Rust","static_stars":"11.6K","tags":["Rust","privacy","security","high-performance"],"category":"core","homepage":null,"paper":null},{"name":"NullClaw","description":"Fastest, smallest, fully autonomous AI assistant infrastructure written in Zig. Part of the Null ecosystem (NullHub UI, NullWatch observability, NullTickets task tracking). Extreme performance with minimal resource footprint.","github":"https://github.com/nullclaw/nullclaw","repo":"nullclaw/nullclaw","language":"Zig","static_stars":"7.1K","tags":["Zig","fastest","smallest","autonomous"],"category":"core","homepage":null,"paper":null},{"name":"TinyAGI","description":"Agent teams orchestrator for One Person Company. Coordinate multiple specialized agents for solo founders and indie researchers. Formerly TinyClaw.","github":"https://github.com/TinyAGI/tinyclaw","repo":"TinyAGI/tinyclaw","language":"TypeScript","static_stars":"3.5K","tags":["orchestrator","one-person-company","multi-agent","indie"],"category":"team","homepage":null,"paper":null},{"name":"FastClaw","description":"Faster and lighter OpenClaw alternative written in Go. Focused on speed, simplicity, and low resource usage. Quick to deploy for researchers who want minimal setup overhead.","github":"https://github.com/fastclaw-ai/fastclaw","repo":"fastclaw-ai/fastclaw","language":"Go","static_stars":"533","tags":["Go","fast","lightweight","alternative"],"category":"core","homepage":null,"paper":null},{"name":"Hermes Agent","description":"The self-improving AI agent by Nous Research. Built-in learning loop — creates skills from experience, improves them during use, nudges itself to persist knowledge, cross-session recall via FTS5 search. 200+ models via OpenRouter. 6 terminal backends (local, Docker, SSH, Daytona, Singularity, Modal). Telegram/Discord/Slack/WhatsApp/Signal. Cron scheduler. Subagent delegation. Research-ready with batch trajectory generation and Atropos RL environments.","github":"https://github.com/NousResearch/hermes-agent","repo":"NousResearch/hermes-agent","language":"Python","static_stars":"41.8K","tags":["Nous Research","self-improving","local-models","per-model-parser","learning-loop"],"category":"core","homepage":null,"paper":null},{"name":"HiClaw","description":"Collaborative Multi-Agent OS by Alibaba. Transparent, human-in-the-loop task coordination via Matrix rooms. Open-source agent team orchestration for enterprise workflows.","github":"https://github.com/alibaba/hiclaw","repo":"alibaba/hiclaw","language":"Shell","static_stars":"4K","tags":["Alibaba","multi-agent","Matrix","human-in-the-loop","enterprise"],"category":"team","homepage":null,"paper":null},{"name":"NemoClaw","description":"NVIDIA official reference stack for running OpenClaw securely inside NVIDIA OpenShell sandbox. Managed inference with Nemotron open-source models. Essential for labs running autonomous agents on GPU servers.","github":"https://github.com/NVIDIA/NemoClaw","repo":"NVIDIA/NemoClaw","language":"JavaScript","static_stars":"18.8K","tags":["NVIDIA","sandbox","security","GPU","Nemotron"],"category":"core","homepage":null,"paper":null},{"name":"OpenSpace","description":"Agent optimization framework from HKUDS (NanoBot team). Makes agents smarter, lower-cost, and self-evolving. Useful for improving any science agent's performance over time.","github":"https://github.com/HKUDS/OpenSpace","repo":"HKUDS/OpenSpace","language":"Python","static_stars":"4.8K","tags":["HKUDS","self-evolving","optimization","low-cost"],"category":"team","homepage":null,"paper":null},{"name":"Edict","description":"Multi-agent orchestration inspired by China's Imperial Three Departments and Six Ministries system. 9 specialized AI agents with real-time dashboard, model config, and full audit trails. You are the Emperor — issue edicts, your AI ministers execute.","github":"https://github.com/cft0808/edict","repo":"cft0808/edict","language":"Python","static_stars":"14.8K","tags":["multi-agent","三省六部","dashboard","audit-trail","12K-stars"],"category":"team","homepage":null,"paper":null},{"name":"ClawTeam","description":"Agent Swarm Intelligence — one command, full automation. Agents spawn swarms, delegate tasks, deliver results. File + ZeroMQ P2P transport. Compatible with Claude Code, Codex, OpenClaw, nanobot, Cursor, any CLI agent. From HKUDS. 4.8K stars.","github":"https://github.com/HKUDS/ClawTeam","repo":"HKUDS/ClawTeam","language":"Python","static_stars":"4.6K","tags":["HKUDS","multi-agent","swarm","coordination"],"category":"team","homepage":null,"paper":null},{"name":"ClawTeam-OpenClaw","description":"ClawTeam fork with deep OpenClaw integration. Default openclaw agent, per-agent session isolation, exec approval auto-config, production-hardened spawn backends. All upstream fixes synced.","github":"https://github.com/win4r/ClawTeam-OpenClaw","repo":"win4r/ClawTeam-OpenClaw","language":"Python","static_stars":"1.1K","tags":["multi-agent","swarm","OpenClaw-native","fork"],"category":"team","homepage":null,"paper":null},{"name":"Biomni","description":"General-purpose biomedical AI agent from Stanford SNAP Lab. Broad coverage across biomedical tasks with a unified agent architecture.","github":"https://github.com/snap-stanford/biomni","repo":"snap-stanford/biomni","language":"Python","static_stars":"2.9K","tags":["Stanford","biomedical","general-purpose","SNAP-Lab"],"category":"bio-omics","homepage":null,"paper":null},{"name":"OriGene","description":"Self-evolving virtual disease biologist for mechanism-guided therapeutic target discovery. Automates disease mechanism analysis and drug target identification.","github":"https://github.com/GENTEL-lab/OriGene","repo":"GENTEL-lab/OriGene","language":"Python","static_stars":"203","tags":["target-discovery","disease-mechanism","self-evolving","drug-target"],"category":"drug-molecular","homepage":null,"paper":null},{"name":"ChemCrow","description":"Pioneering chemistry AI agent (2023) from ur-whitelab. LangChain-based, cited in official docs. The foundational project that inspired MDCrow and the broader science agent movement.","github":"https://github.com/ur-whitelab/chemcrow-public","repo":"ur-whitelab/chemcrow-public","language":"Python","static_stars":"894","tags":["chemistry","pioneer","LangChain","ur-whitelab"],"category":"drug-molecular","homepage":null,"paper":null},{"name":"STELLA","description":"Self-evolving multimodal agent platform for biomedical research. From Princeton/Stanford/UCLA. Published on bioRxiv and arXiv. Live demo at stella-agent.com.","github":"https://github.com/zaixizhang/STELLA","repo":"zaixizhang/STELLA","language":"Python","static_stars":"124","tags":["Princeton","Stanford","multimodal","self-evolving","bioRxiv"],"category":"science","homepage":"https://stella-agent.com","paper":"https://arxiv.org/abs/2507.02004"},{"name":"BioOS-Claws","description":"BioOS platform integration for OpenClaw agents. JavaScript-based, actively developed.","github":"https://github.com/GBA-BI/BioOS-Claws","repo":"GBA-BI/BioOS-Claws","language":"JavaScript","static_stars":"1","tags":["BioOS","platform","early-stage"],"category":"bio-omics","homepage":null,"paper":null},{"name":"NanoResearch","description":"End-to-end autonomous AI research engine that actually runs experiments. 9-stage pipeline: idea → literature → code → GPU/SLURM training → real results → figures → LaTeX paper. Every data point, table, and chart comes from actual experiments, not LLM fabrication. CLI with TUI, Claude Code mode, Feishu bot. Local or cluster execution.","github":"https://github.com/OpenRaiser/NanoResearch","repo":"OpenRaiser/NanoResearch","language":"Python","static_stars":"698","tags":["NanoBot-based","autonomous","research-assistant"],"category":"general-research","homepage":null,"paper":null},{"name":"EpiClaw","description":"Epidemiology AI agent from GBA-BI. Extends OpenClaw with epidemic prevention, early warning, epidemiological analysis, and BioOS integration.","github":"https://github.com/GBA-BI/EpiClaw","repo":"GBA-BI/EpiClaw","language":"Python","static_stars":"8","tags":["epidemiology","GBA-BI","BioOS","early-stage"],"category":"bio-omics","homepage":null,"paper":null},{"name":"PantheonOS","description":"Evolvable, distributed agent framework for data science from the dynamo/Spateo team. Specialized in single-cell and spatial transcriptomics workflows.","github":"https://github.com/aristoteleo/PantheonOS","repo":"aristoteleo/PantheonOS","language":"Python","static_stars":"388","tags":["dynamo-team","single-cell","spatial-transcriptomics","distributed"],"category":"bio-omics","homepage":null,"paper":null},{"name":"OmicClaw","description":"OmicVerse agent skill. Connects the OmicVerse computational biology framework to OpenClaw agents.","github":"https://github.com/Starlitnightly/omicclaw","repo":"Starlitnightly/omicclaw","language":"JavaScript","static_stars":"26","tags":["OmicVerse","agent-skill","computational-biology"],"category":"bio-omics","homepage":null,"paper":null},{"name":"ClawManager","description":"Kubernetes-first control plane for managing OpenClaw and Linux desktop runtimes at team and cluster scale. Web UI for multi-instance orchestration.","github":"https://github.com/Yuan-lab-LLM/ClawManager","repo":"Yuan-lab-LLM/ClawManager","language":"TypeScript","static_stars":"531","tags":["Kubernetes","cluster-management","control-plane","web-UI"],"category":"team","homepage":null,"paper":null},{"name":"autoresearch","description":"By Andrej Karpathy. Give an AI agent a small but real LLM training setup and let it experiment autonomously overnight. Single GPU, ~100 experiments/night. Works with Claude Code, Codex, or any agent.","github":"https://github.com/karpathy/autoresearch","repo":"karpathy/autoresearch","language":"Python","static_stars":"69.2K","tags":["Karpathy","autonomous","LLM-training","single-GPU"],"category":"general-research","homepage":null,"paper":null},{"name":"DeepResearch","description":"Tongyi Deep Research by Alibaba. Leading open-source deep research agent (30.5B params, 3.3B activated). State-of-the-art on Humanity's Last Exam, BrowseComp, and 4 more benchmarks. ReAct and IterResearch inference modes.","github":"https://github.com/Alibaba-NLP/DeepResearch","repo":"Alibaba-NLP/DeepResearch","language":"Python","static_stars":"18.6K","tags":["Alibaba","Tongyi","deep-research","benchmark-SOTA"],"category":"general-research","homepage":null,"paper":null},{"name":"AgentLaboratory","description":"End-to-end autonomous research workflow: Literature Review → Experimentation → Report Writing. Specialized LLM agents collaborate via arXiv, HuggingFace, Python, LaTeX. Includes AgentRxiv for cumulative cross-agent research.","github":"https://github.com/SamuelSchmidgall/AgentLaboratory","repo":"SamuelSchmidgall/AgentLaboratory","language":"Python","static_stars":"5.5K","tags":["multi-agent","end-to-end","AgentRxiv","autonomous"],"category":"general-research","homepage":null,"paper":null},{"name":"ARIS","description":"ARIS v0.4.1 — Lightweight autonomous ML research skills. 62 skills for cross-model review loops, idea discovery, experiment automation. Now with standalone CLI, Plan mode, Research Wiki (persistent knowledge base), Self-Evolution (/meta-optimize), local model support (LM Studio/Ollama). Works with Claude Code, Codex, OpenClaw, any LLM agent. No framework lock-in.","github":"https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep","repo":"wanshuiyin/Auto-claude-code-research-in-sleep","language":"Python","static_stars":"5.9K","tags":["Claude-Code","sleep-research","cross-model","Markdown-skills"],"category":"specialized","homepage":null,"paper":null},{"name":"Auto-Deep-Research","description":"Open-source, cost-efficient alternative to OpenAI's Deep Research, built on AutoAgent framework by HKUDS. Universal LLM support (OpenAI, Anthropic, DeepSeek, vLLM, Grok). One-click launch.","github":"https://github.com/HKUDS/Auto-Deep-Research","repo":"HKUDS/Auto-Deep-Research","language":"Python","static_stars":"1.5K","tags":["HKUDS","deep-research","cost-efficient","universal-LLM"],"category":"general-research","homepage":null,"paper":null},{"name":"OpenResearcher","description":"Fully open agentic LLM (30B-A3B) for long-horizon deep research by TIGER-AI-Lab. 54.8% on BrowseComp-Plus, surpassing GPT-4.1, Claude-Opus-4, Gemini-2.5-Pro. Open dataset (96K trajectories), model, and training code. Adopted by NVIDIA Nemotron.","github":"https://github.com/TIGER-AI-Lab/OpenResearcher","repo":"TIGER-AI-Lab/OpenResearcher","language":"Python","static_stars":"635","tags":["TIGER-AI-Lab","open-source","BrowseComp","NVIDIA-Nemotron"],"category":"general-research","homepage":null,"paper":null},{"name":"freephdlabor","description":"Personalized multi-agent system that researches 24/7 on your scientific problem. From hypothesis generation through experimentation to publication-ready manuscripts. Dynamic workflows, fully customizable agents, human-in-the-loop.","github":"https://github.com/ltjed/freephdlabor","repo":"ltjed/freephdlabor","language":"Python","static_stars":"496","tags":["24/7-research","multi-agent","customizable","paper-generation"],"category":"general-research","homepage":null,"paper":null},{"name":"CodeScientist","description":"Automated scientific discovery system by Allen AI. LLM-as-a-mutator generates experiment ideas from paper+code combinations, then creates, runs, and debugs experiments in containers. Writes reports and meta-analyses.","github":"https://github.com/allenai/codescientist","repo":"allenai/codescientist","language":"Python","static_stars":"324","tags":["Allen-AI","code-experiments","genetic-mutation","discovery"],"category":"specialized","homepage":null,"paper":null},{"name":"OmniScientist","description":"AI Scientist Ecosystem by Tsinghua FIB Lab and Zhongguancun Academy. 7 core papers covering co-evolving ecosystem, expert knowledge integration, high-impact research question identification, and automated experiment design.","github":"https://github.com/tsinghua-fib-lab/OmniScientist","repo":"tsinghua-fib-lab/OmniScientist","language":"Python","static_stars":"120","tags":["Tsinghua","ecosystem","multi-paper","full-process"],"category":"general-research","homepage":null,"paper":null},{"name":"autoBioResearch","description":"Autonomous biological knowledge graph builder. Searches PubMed and Semantic Scholar, extracts entities/interactions with LLM, stores in SQLite, detects contradictory claims, and generates follow-up queries. Local pipeline, no cloud dependencies.","github":"https://github.com/JMGamma/autoBioResearch","repo":"JMGamma/autoBioResearch","language":"Python","static_stars":"1","tags":["biology","knowledge-graph","PubMed","autonomous"],"category":"bio-omics","homepage":null,"paper":null},{"name":"ResearchClawBench","description":"Benchmark for evaluating whether AI agents can independently conduct scientific research. 40 real-science tasks across 10 disciplines (Astronomy, Chemistry, Physics, Life, etc.), two-stage pipeline (autonomous research + LLM peer-review scoring), expert-annotated checklists. Score 50 = match human paper, 70+ = surpass it. Supports Claude Code, Codex CLI, OpenClaw, NanoBot, EvoScientist. From Shanghai Jiao Tong University.","github":"https://github.com/InternScience/ResearchClawBench","repo":"InternScience/ResearchClawBench","language":"Jupyter Notebook","static_stars":"67","tags":["benchmark","evaluation","multi-agent","scientific-research","SJTU"],"category":"benchmark","homepage":null,"paper":null},{"name":"NeuroClaw","description":"Neuroscience AI agent from CUHK AIM Group. Early stage — no description yet, actively developed.","github":"https://github.com/CUHK-AIM-Group/NeuroClaw","repo":"CUHK-AIM-Group/NeuroClaw","language":"Python","static_stars":"14","tags":["CUHK","neuroscience","early-stage"],"category":"bio-omics","homepage":null,"paper":null},{"name":"MagiClaw","description":"Conversational command center for scientific agent teams. From SJTU SAI Agents. Orchestrate multiple research agents through natural language dialogue.","github":"https://github.com/sjtu-sai-agents/MagiClaw","repo":"sjtu-sai-agents/MagiClaw","language":"Python","static_stars":"107","tags":["SJTU","command-center","multi-agent","conversational"],"category":"team","homepage":null,"paper":null},{"name":"AlphaClaw","description":"The ultimate OpenClaw harness. Browser-based setup wizard, self-healing watchdog, Git-backed rollback, multi-agent management, prompt hardening, and one-click Railway/Render deploy. 892 stars, 440 tests. Zero SSH rescue missions.","github":"https://github.com/chrysb/alphaclaw","repo":"chrysb/alphaclaw","language":"JavaScript","static_stars":"1.1K","tags":["devops","deployment","watchdog","multi-agent","observability"],"category":"team","homepage":null,"paper":null},{"name":"BioMedAgent","description":"Biomedical AI agent published in Nature Biomedical Engineering. Dormant since Feb 2025 but with top-tier publication backing.","github":"https://github.com/BOBQWERA/BioMedAgent","repo":"BOBQWERA/BioMedAgent","language":"Python","static_stars":"57","tags":["Nature-BME","biomedical","dormant"],"category":"bio-omics","homepage":null,"paper":"https://www.nature.com/articles/s41551-026-01634-6"},{"name":"Memento-Skills","description":"Let Agents Design Agents. A meta-framework where AI agents create, test, and evolve new skills and agents autonomously. Unlike traditional skill libraries, the skills here are machine-authored.","github":"https://github.com/Memento-Teams/Memento-Skills","repo":"Memento-Teams/Memento-Skills","language":"Python","static_stars":"1K","tags":["meta-framework","agent-designs-agent","self-evolving","autonomous"],"category":"specialized","homepage":null,"paper":null},{"name":"OpenHarness","description":"Open Agent Harness from HKUDS (NanoBot team). Runtime environment and execution framework for AI agents. 615 stars in 1 day.","github":"https://github.com/HKUDS/OpenHarness","repo":"HKUDS/OpenHarness","language":"Python","static_stars":"8K","tags":["HKUDS","harness","runtime","agent-infrastructure"],"category":"core","homepage":null,"paper":null},{"name":"PinchBench","description":"Real-world benchmarks for AI coding agents. 23 tasks across productivity, research, writing, coding, analysis, email, memory, and skills. Public leaderboard at pinchbench.com. Auto-grading + LLM judge. Tests what actually matters: tool usage, multi-step reasoning, and practical outcomes.","github":"https://github.com/pinchbench/skill","repo":"pinchbench/skill","language":"Python","static_stars":"965","tags":["benchmark","evaluation","coding-agent","leaderboard","OpenClaw"],"category":"benchmark","homepage":"https://pinchbench.com","paper":null},{"name":"HeurekaBench","description":"ICLR 2026 framework to create benchmarks and evaluate AI co-scientists in experimental data-driven scientific research. From EPFL Machine Learning & Bioinformatics Lab.","github":"https://github.com/mlbio-epfl/HeurekaBench","repo":"mlbio-epfl/HeurekaBench","language":"Python","static_stars":"11","tags":["benchmark","evaluation","AI-co-scientist","ICLR","EPFL"],"category":"benchmark","homepage":null,"paper":"https://arxiv.org/abs/2601.01678"},{"name":"ClawKeeper","description":"Security scanner for AI agent hosts. 42 checks across 5 phases: host hardening, network, prerequisites, installation, security audit. Auto-fix for firewalls, encryption, permissions. Credential exposure detection in configs/history/logs. Pure bash, zero dependencies. By RAD Security.","github":"https://github.com/rad-security/clawkeeper","repo":"rad-security/clawkeeper","language":"Bash","static_stars":"10","tags":["security","scanner","hardening","audit","OpenClaw"],"category":"security","homepage":"https://clawkeeper.dev","paper":null},{"name":"NeuriCo","description":"Autonomous research framework from University of Chicago Human+AI Lab. Input a title, domain, and hypothesis — agents handle literature review, experiment design, code execution, analysis, and LaTeX paper writing. Supports Claude Code, Codex, and Gemini CLI. IdeaHub platform for community research ideas. Docker-ready, domain-agnostic.","github":"https://github.com/ChicagoHAI/NeuriCo","repo":"ChicagoHAI/NeuriCo","language":"Python","static_stars":"83","tags":["autonomous-research","multi-provider","IdeaHub","UChicago","paper-writing"],"category":"general-research","homepage":null,"paper":null},{"name":"DeepScientist","description":"Local-first AI research studio. 15-minute setup, one repo per research quest, visible progress, human takeover anytime. Published at ICLR 2026.","github":"https://github.com/ResearAI/DeepScientist","repo":"ResearAI/DeepScientist","language":"TypeScript","static_stars":"1.9K","tags":["ICLR-2026","local-first","research-studio","human-in-the-loop"],"category":"specialized","homepage":"https://deepscientist.cc","paper":"https://openreview.net/forum?id=cZFgsLq8Gs"},{"name":"autoagent","description":"Autonomous harness engineering. Self-configuring agent runtime that adapts to your workflow. 560 stars in 24 hours.","github":"https://github.com/kevinrgu/autoagent","repo":"kevinrgu/autoagent","language":"Python","static_stars":"3.9K","tags":["harness","autonomous","runtime","self-configuring"],"category":"core","homepage":null,"paper":null},{"name":"StatsClaw","description":"Multi-agent workflow for statistical software development. Information-isolated agents: builder (no ground truth), simulator (no algorithm), tester (independent validation). Cambridge + Stanford.","github":"https://github.com/statsclaw/statsclaw","repo":"statsclaw/statsclaw","language":"Python","static_stars":"55","tags":["Cambridge","Stanford","statistics","R-packages","multi-agent"],"category":"specialized","homepage":"https://statsclaw.ai","paper":"https://bit.ly/statsclaw"},{"name":"Open Multi-Agent","description":"TypeScript multi-agent framework. One runTeam() call from goal to result. Auto task decomposition, parallel execution. 3 dependencies, deploys anywhere Node.js runs. 4K stars in 4 days.","github":"https://github.com/JackChen-me/open-multi-agent","repo":"JackChen-me/open-multi-agent","language":"TypeScript","static_stars":"5.5K","tags":["multi-agent","TypeScript","lightweight","parallel-execution"],"category":"team","homepage":null,"paper":null},{"name":"TCM-Agent","description":"LLM-powered multi-agent system for Traditional Chinese Medicine network pharmacology. Compound query (PubChem), target analysis (TTD), molecular similarity (Morgan/MACCS fingerprints), enrichment analysis (GO/KEGG), and TCM-target knowledge graphs. Flask + React frontend with DeepSeek/Doubao support.","github":"https://github.com/AITCM/TCM-Agent","repo":"AITCM/TCM-Agent","language":"Python","static_stars":"11","tags":["tcm","network-pharmacology","drug-discovery","knowledge-graph","multi-agent"],"category":"drug-molecular","homepage":null,"paper":null},{"name":"ClawSafety (Benchmark)","description":"Safety benchmark for personal AI agents under realistic prompt injection. 120 adversarial test cases across 5 harm domains, 3 attack vectors, and 5 harmful action types. Tested Claude, Gemini, GPT-5.1, DeepSeek on OpenClaw/Nanobot/NemoClaw scaffolds. Key finding: chat safety ≠ agent safety.","github":"https://github.com/weibowen555/ClawSafety","repo":"weibowen555/ClawSafety","language":"Python","static_stars":"2","tags":["safety","benchmark","prompt-injection","adversarial"],"category":"benchmark","homepage":null,"paper":"https://arxiv.org/abs/2604.01438"},{"name":"ClawSafety (Scanner)","description":"Security scanner for Agent Skills — the npm audit for the Agent-Native ecosystem. Scans for shell injection, hardcoded secrets, unpinned dependencies, excessive permissions, and prompt injection risks. Rust CLI with GitHub App integration. Inspired by the ClawHavoc incident (341 malicious skills).","github":"https://github.com/relaxcloud-cn/clawsafety","repo":"relaxcloud-cn/clawsafety","language":"Rust","static_stars":"1","tags":["security","scanner","skills","vulnerability"],"category":"security","homepage":null,"paper":null},{"name":"PyMolClaw","description":"Molecular visualization skill powered by PyMOL. Natural language → publication-quality figures. 13 scripts: structure alignment, binding sites, Goodsell-style illustrations, surface rendering, mutation analysis, cryo-EM density maps, and animations.","github":"https://github.com/junior1p/PyMolClaw","repo":"junior1p/PyMolClaw","language":"Python","static_stars":"1","tags":["PyMOL","molecular-visualization","structural-biology","skill"],"category":"drug-molecular","homepage":null,"paper":null},{"name":"MathClaw","description":"Multimodal math learning assistant for middle and high school. Solving workspace, weakness diagnosis, knowledge graphs, error graphs, auto-summaries. Supports WeChat, QQ, Feishu, Telegram, Discord. From Renmin University.","github":"https://github.com/MathClaw-ruc/MathClaw","repo":"MathClaw-ruc/MathClaw","language":"Python","static_stars":"62","tags":["education","mathematics","multimodal","knowledge-graph","Renmin-University"],"category":"education","homepage":null,"paper":null},{"name":"Claw-Eval","description":"End-to-end evaluation suite for autonomous agents. 300 human-verified tasks across 9 categories (service orchestration, multimodal perception, multi-turn dialogue). Trajectory-aware grading over 2,159 rubrics. Tests Completion, Safety, and Robustness. Used by Qwen, GLM, MiniMax.","github":"https://github.com/claw-eval/claw-eval","repo":"claw-eval/claw-eval","language":"Python","static_stars":"352","tags":["benchmark","evaluation","multimodal","trajectory-aware","safety"],"category":"benchmark","homepage":"https://claw-eval.github.io","paper":null},{"name":"BloClaw","description":"Omniscient multi-modal agentic workspace for scientific discovery. Cheminformatics (RDKit), protein folding (ESMFold), molecular docking, autonomous RAG. XML-Regex dual-track routing, runtime sandbox for data visualization. From Beijing 1st Biotech + PLA General Hospital.","github":"https://github.com/qinheming/BIoClaw","repo":"qinheming/BIoClaw","language":"Python","static_stars":"1","tags":["multi-modal","cheminformatics","protein-folding","molecular-docking","RAG"],"category":"drug-molecular","homepage":null,"paper":"https://arxiv.org/abs/2604.00550"},{"name":"HealthClaw","description":"Open-source self-evolving personal health copilot. Medical consultation support, meal planning, report interpretation, chronic-care follow-up, wearable data analytics. Supports clinical data, medical imaging, and omics evidence. Streamlit + Feishu + CLI.","github":"https://github.com/HC-Guo/HealthClaw","repo":"HC-Guo/HealthClaw","language":"Python","static_stars":"255","tags":["health","medical","self-evolving","wearable","omics"],"category":"science","homepage":null,"paper":null},{"name":"BioAgent Bench","description":"AI agent evaluation suite for bioinformatics. Benchmarks LLM agents on real bioinformatics tasks. Covers sequence analysis, genomics workflows, and computational biology pipelines. arXiv paper.","github":"https://github.com/bioagent-bench/bioagent-bench","repo":"bioagent-bench/bioagent-bench","language":"Python","static_stars":"16","tags":["benchmark","bioinformatics","evaluation","LLM-agent"],"category":"benchmark","homepage":null,"paper":"https://arxiv.org/abs/2601.21800"},{"name":"Multica","description":"Open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills. Agents show up on boards, post comments, report blockers autonomously. Works with Claude Code, Codex, OpenClaw. Self-hosted or cloud (multica.ai).","github":"https://github.com/multica-ai/multica","repo":"multica-ai/multica","language":"TypeScript","static_stars":"3874","tags":["managed-agents","task-management","multi-agent","self-hosted"],"category":"team","homepage":"https://multica.ai","paper":null},{"name":"AI-Scientist (v1)","description":"The original fully automated AI scientist from Sakana AI. Autonomously generates ideas, runs experiments, writes research papers, and conducts peer review. First open-source system to close the full research loop. 13K+ stars.","github":"https://github.com/SakanaAI/AI-Scientist","repo":"SakanaAI/AI-Scientist","language":"Jupyter Notebook","static_stars":"13219","tags":["Sakana-AI","end-to-end","autonomous","paper-generation"],"category":"general-research","homepage":null,"paper":null},{"name":"pi-autoresearch","description":"Generic version of Karpathy's autoresearch loop that works on any measurable optimization target. Modify → run → score → keep/discard → repeat. Not limited to ML — works for any codebase with a metric.","github":"https://github.com/davebcn87/pi-autoresearch","repo":"davebcn87/pi-autoresearch","language":"TypeScript","static_stars":"3585","tags":["autoresearch","optimization-loop","generic","any-metric"],"category":"general-research","homepage":null,"paper":null},{"name":"autoresearch (uditgoenka)","description":"Multi-purpose Claude Code plugin: autonomous goal-directed iteration inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat. Also includes debug, fix, security audit, ship, and predict modes.","github":"https://github.com/uditgoenka/autoresearch","repo":"uditgoenka/autoresearch","language":"Shell","static_stars":"3659","tags":["Claude-Code","autoresearch","multi-mode","skill"],"category":"general-research","homepage":null,"paper":null},{"name":"InternAgent","description":"Unified long-horizon scientist framework from InternScience. Links deep research, executable verification, and memory-driven evolution across algorithm and empirical discovery. v1.5 with Web UI.","github":"https://github.com/InternScience/InternAgent","repo":"InternScience/InternAgent","language":"Python","static_stars":"1271","tags":["InternScience","long-horizon","end-to-end","memory-evolution"],"category":"general-research","homepage":null,"paper":null},{"name":"autoresearch-mlx","description":"Karpathy's autoresearch loop adapted for Apple Silicon Macs using MLX. No PyTorch required — runs natively on M-series chips. Overnight autonomous experiment optimization.","github":"https://github.com/trevin-creator/autoresearch-mlx","repo":"trevin-creator/autoresearch-mlx","language":"Python","static_stars":"1406","tags":["Apple-Silicon","MLX","autoresearch","Mac-native"],"category":"general-research","homepage":null,"paper":null},{"name":"Kosmos","description":"Autonomous discovery engine that tests hypotheses in sandboxed containers and tracks findings in a knowledge graph. Driven by Claude Code or API. Based on the Kosmos AI paper (arXiv:2511.02824).","github":"https://github.com/jimmc414/Kosmos","repo":"jimmc414/Kosmos","language":"Python","static_stars":"495","tags":["autonomous-discovery","knowledge-graph","sandboxed","hypothesis-testing"],"category":"general-research","homepage":null,"paper":"https://arxiv.org/abs/2511.02824"},{"name":"ClawBench","description":"Real-world web task benchmark for AI agents. 153 tasks across 15 life categories on 144 live websites. Claude Sonnet 4.6 achieves only 33.3%, GPT-5.4 only 6.5% — highlighting the gap between sandbox and real-world performance. From UBC, Vector Institute, CMU, SJTU, Tsinghua.","github":"https://github.com/reacher-z/ClawBench","repo":"reacher-z/ClawBench","language":"Python","static_stars":"47","tags":["benchmark","web-tasks","real-world","153-tasks","multi-university"],"category":"benchmark","homepage":"https://claw-bench.com","paper":null},{"name":"ClawMark","description":"Multi-day, multimodal coworker agent benchmark. 100 tasks across 13 professional domains (insurance, legal, EDA, etc). Environment changes dynamically — new emails, file updates, schedule shifts. Cross-modal multi-turn with branching logic. Best score only 55%. From NUS, Evolvent AI, HKU, MIT, UW, UC Berkeley, CUHK, HKUST (40+ scholars).","github":"https://github.com/evolvent-ai/clawmark","repo":"evolvent-ai/clawmark","language":"Python","static_stars":"51","tags":["benchmark","multi-day","multimodal","dynamic-environment","NUS-MIT-Berkeley"],"category":"benchmark","homepage":"https://claw-mark.com","paper":null}],"skills":[{"name":"skill-vetter","description":"Security vetting checklist for AI agent skills. 4-step protocol: source authentication, code review with explicit rejection criteria, permission scope evaluation, and risk classification (low → extreme). No code, no dependencies — just a battle-tested review process.","github":null,"repo":null,"tags":["Editor's Pick","security","vetting","3K-downloads","must-have"],"category":"security","install_command":"clawhub install skill-vetter"},{"name":"openalex-database","description":"Search 240M+ scholarly works across all fields. Author/institution analysis, citation tracking, open-access discovery. Completely free, no API key needed. The best all-around starting point.","github":"https://github.com/K-Dense-AI/claude-scientific-skills","repo":"K-Dense-AI/claude-scientific-skills","tags":["Editor's Pick","240M papers","no-key-needed","all-fields"],"category":"literature","install_command":"clawhub install openalex-database"},{"name":"pubmed-database","description":"Best for biomedical research. Advanced Boolean/MeSH queries, batch processing, filter by RCT/meta-analysis/systematic review. The gold standard for life sciences literature.","github":"https://github.com/K-Dense-AI/claude-scientific-skills","repo":"K-Dense-AI/claude-scientific-skills","tags":["biomedical","MeSH","no-key-needed"],"category":"literature","install_command":"clawhub install pubmed-database"},{"name":"arxiv-database","description":"Best for CS/ML/physics/math preprints. Search by keywords, authors, IDs, date ranges, and 8 category groups. No key needed.","github":"https://github.com/K-Dense-AI/claude-scientific-skills","repo":"K-Dense-AI/claude-scientific-skills","tags":["CS/ML/physics","preprints","no-key-needed"],"category":"literature","install_command":"clawhub install arxiv-database"},{"name":"aminer-data-search","description":"Best for exploring scholar networks. 28 APIs for scholar/paper/institution/journal/patent queries. Natural language Q&A like \"latest advances in Transformers\".","github":"https://github.com/CanXiangCC/aminer-open-skill","repo":"CanXiangCC/aminer-open-skill","tags":["scholar-network","patent","28-APIs","needs-key"],"category":"literature","install_command":"cp -r skills/aminer-data-search ~/.claude/skills/"},{"name":"deep-research","description":"The most comprehensive single skill for literature review. 13 agents, 7 modes: full research, quick brief, paper review, PRISMA systematic review with meta-analysis, Socratic dialogue, and fact-check. Unmatched depth.","github":"https://github.com/Imbad0202/academic-research-skills","repo":"Imbad0202/academic-research-skills","tags":["Editor's Pick","13-agents","PRISMA","meta-analysis"],"category":"review","install_command":"git clone https://github.com/Imbad0202/academic-research-skills.git && cp -r academic-research-skills/deep-research ~/.claude/skills/"},{"name":"lit-synthesizer","description":"Best for finding research gaps. PubMed MeSH + bioRxiv/medRxiv search with citation graph construction and gap analysis. Identifies understudied areas. No extra key needed.","github":"https://github.com/ClawBio/ClawBio","repo":"ClawBio/ClawBio","tags":["citation-graph","gap-analysis","no-key-needed"],"category":"review","install_command":"clawhub install lit-synthesizer"},{"name":"literature-review","description":"Solid all-rounder for systematic reviews. PRISMA-style searches, cross-database synthesis, citation verification. Outputs in APA/Nature/Vancouver format.","github":"https://github.com/K-Dense-AI/claude-scientific-skills","repo":"K-Dense-AI/claude-scientific-skills","tags":["systematic-review","PRISMA","multi-format"],"category":"review","install_command":"clawhub install literature-review"},{"name":"medical-research-toolkit","description":"14+ biomedical databases unified in one skill: ChEMBL, PubMed, ClinicalTrials.gov, OpenTargets, OpenFDA, OMIM, Reactome, KEGG, UniProt. Drug repurposing, target discovery, and more.","github":"https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills","repo":"FreedomIntelligence/OpenClaw-Medical-Skills","tags":["Editor's Pick","14-databases","drug-repurposing","needs-MCP"],"category":"data","install_command":"clawhub install medical-research-toolkit"},{"name":"AIPOCH Evidence Insights","description":"200+ medical research skills covering the full workflow. R/Python bioinformatics code generation, statistical modeling, ML pipelines, data cleaning, and visualization.","github":"https://github.com/aipoch/medical-research-skills","repo":"aipoch/medical-research-skills","tags":["200-skills","R/Python","bioinformatics","OpenClaw-native"],"category":"data","install_command":"bash <(curl -s https://raw.githubusercontent.com/aipoch/medical-research-skills/main/scientific-skills/scripts/openclaw-install.sh)"},{"name":"autoresearch","description":"End-to-end autonomous AI research pipeline: literature survey → experiment → paper. Two-loop architecture for overnight runs. Best for ML/AI research experiments.","github":"https://github.com/Orchestra-Research/AI-Research-SKILLs","repo":"Orchestra-Research/AI-Research-SKILLs","tags":["end-to-end","overnight","ML/AI-research"],"category":"data","install_command":"npx @orchestra-research/ai-research-skills"},{"name":"academic-pipeline","description":"10-stage academic writing pipeline: research → draft → peer review → revise → finalize. Multi-perspective review with 0-100 rubrics. Outputs APA 7.0, IEEE, or Chicago format.","github":"https://github.com/Imbad0202/academic-research-skills","repo":"Imbad0202/academic-research-skills","tags":["Editor's Pick","10-stage","peer-review","APA/IEEE/Chicago"],"category":"writing","install_command":"git clone https://github.com/Imbad0202/academic-research-skills.git && cp -r academic-research-skills/academic-paper ~/.claude/skills/"},{"name":"latex-paper-conversion","description":"Convert academic LaTeX papers between publisher formats: Springer → MDPI, IEEE → Nature, etc. Automates template injection and compilation debugging.","github":"https://github.com/sickn33/antigravity-awesome-skills","repo":"sickn33/antigravity-awesome-skills","tags":["LaTeX","format-conversion","no-key-needed"],"category":"writing","install_command":"clawhub install latex-paper-conversion"},{"name":"citation-management","description":"Multi-source citation tool: Google Scholar + PubMed + CrossRef + arXiv. DOI/PMID/arXiv ID to BibTeX. Validates citations to prevent AI-fabricated references.","github":"https://github.com/K-Dense-AI/claude-scientific-skills","repo":"K-Dense-AI/claude-scientific-skills","tags":["Editor's Pick","BibTeX","anti-hallucination","no-key-needed"],"category":"citation","install_command":"clawhub install citation-management"},{"name":"ARIS /idea-discovery","description":"Full autonomous pipeline: literature scan → idea creation → novelty check → peer review → iterative refinement. From a topic to a validated, pilot-tested research plan.","github":"https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep","repo":"wanshuiyin/Auto-claude-code-research-in-sleep","tags":["Editor's Pick","autonomous","idea-to-plan","overnight"],"category":"ideation","install_command":"git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git && cp -r Auto-claude-code-research-in-sleep/skills/idea-discovery ~/.claude/skills/"},{"name":"ARIS /novelty-check","description":"Verify if your research idea is truly novel. Extracts 3-5 core claims, searches each independently, then runs adversarial cross-model review to probe blind spots.","github":"https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep","repo":"wanshuiyin/Auto-claude-code-research-in-sleep","tags":["novelty-verification","adversarial-review","cross-model"],"category":"ideation","install_command":"git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git && cp -r Auto-claude-code-research-in-sleep/skills/novelty-check ~/.claude/skills/"},{"name":"scrna-orchestrator","description":"End-to-end scRNA-seq pipeline in one skill. QC → doublet removal → normalization → HVG → PCA/scVI → UMAP → Leiden → marker genes → cell type annotation → report. Generates a full reproducibility bundle.","github":"https://github.com/ClawBio/ClawBio","repo":"ClawBio/ClawBio","tags":["Editor's Pick","end-to-end","scanpy","reproducible"],"category":"scrna","install_command":"clawhub install scrna-orchestrator"},{"name":"bio-single-cell-cell-annotation","description":"Automated cell type annotation with three engines: CellTypist (deep learning, 100+ tissue models), SingleR (reference-based, R), and Azimuth (Seurat reference mapping). The most comprehensive annotation skill available.","github":"https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills","repo":"FreedomIntelligence/OpenClaw-Medical-Skills","tags":["CellTypist","SingleR","Azimuth","annotation"],"category":"scrna","install_command":"clawhub install bio-single-cell-cell-annotation"},{"name":"scvelo","description":"RNA velocity analysis: cell-state transitions, developmental trajectories, latent time estimation, and driver gene identification. Dynamical mode for maximum accuracy.","github":"https://github.com/K-Dense-AI/claude-scientific-skills","repo":"K-Dense-AI/claude-scientific-skills","tags":["RNA-velocity","trajectory","pseudotime","driver-genes"],"category":"scrna","install_command":"clawhub install scvelo"}],"skill_hubs":[{"name":"Anthropic Skills","description":"Official Agent Skills repository by Anthropic. The canonical source for Claude Code skills — community contributions, curated quality, and production-ready templates.","github":"https://github.com/anthropics/skills","repo":"anthropics/skills","tags":["Anthropic","official","Claude Code","101K stars"],"category":"registry","homepage":null},{"name":"ClawHub","description":"The official OpenClaw skill registry. Publish, version, search, and install text-based agent skills. 6,300+ skills with vector search, starring, commenting, and admin curation.","github":"https://github.com/openclaw/clawhub","repo":"openclaw/clawhub","tags":["official","registry","6300+ skills","vector-search"],"category":"registry","homepage":"https://clawhub.ai"},{"name":"ClawHub China Mirror","description":"Official ClawHub mirror for mainland China. Same 6,300+ skills, accelerated access without VPN. Full registry sync, search, and install support.","github":null,"repo":null,"tags":["official","mirror","China","accelerated"],"category":"registry","homepage":"http://mirror-cn.clawhub.com"},{"name":"Awesome OpenClaw Skills","description":"5,400+ community skills filtered and categorized from the official Skills Registry. Install via clawhub install <slug> or manual copy. Maintained by VoltAgent.","github":"https://github.com/VoltAgent/awesome-openclaw-skills","repo":"VoltAgent/awesome-openclaw-skills","tags":["awesome-list","5400+ skills","categorized","curated"],"category":"general","homepage":null},{"name":"K-Dense Scientific Skills","description":"170+ ready-to-use skills across 17 scientific domains: bioinformatics, cheminformatics, proteomics, clinical research, materials science, physics, and more. Connected to 250+ databases.","github":"https://github.com/K-Dense-AI/claude-scientific-skills","repo":"K-Dense-AI/claude-scientific-skills","tags":["170+ skills","17 domains","250+ databases","multi-disciplinary"],"category":"science","homepage":null},{"name":"AI Research Skills","description":"86 skills across 22 categories for autonomous AI research. Covers ideation, ML paper writing, fine-tuning, distributed training, inference, safety, agents, RAG, multimodal, and more.","github":"https://github.com/Orchestra-Research/AI-Research-SKILLs","repo":"Orchestra-Research/AI-Research-SKILLs","tags":["86 skills","22 categories","ML research","paper-writing"],"category":"science","homepage":null},{"name":"Academic Research Skills","description":"Full academic pipeline: 13-agent deep research team, 12-agent paper writing (LaTeX/DOCX/MD), multi-perspective peer review with scoring rubrics, and 10-stage pipeline orchestrator.","github":"https://github.com/Imbad0202/academic-research-skills","repo":"Imbad0202/academic-research-skills","tags":["academic-writing","peer-review","LaTeX","pipeline"],"category":"science","homepage":null},{"name":"OpenClaw Medical Skills","description":"The largest open-source medical AI skills library. 869 curated skills covering clinical, genomics, drug discovery, bioinformatics. Connected to PubMed, ClinicalTrials.gov, ChEMBL, DrugBank.","github":"https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills","repo":"FreedomIntelligence/OpenClaw-Medical-Skills","tags":["869 skills","clinical","drug-discovery","PubMed"],"category":"medical","homepage":null},{"name":"ClawBio","description":"Bioinformatics-native AI agent skill library. 24 skills + 8,000 Galaxy tools. Local-first, reproducible. Features pharmacogenomics, GWAS lookup, polygenic risk scores, UK Biobank queries.","github":"https://github.com/ClawBio/ClawBio","repo":"ClawBio/ClawBio","tags":["bioinformatics","Galaxy-tools","local-first","reproducible"],"category":"medical","homepage":null},{"name":"SkillHub","description":"Tencent official OpenClaw skills community, optimized for Chinese users. Browse, share, and install curated AI agent skills with WeChat integration.","github":null,"repo":null,"tags":["Tencent","official","Chinese-community","WeChat"],"category":"registry","homepage":"https://skillhub.tencent.com"},{"name":"STELLA","description":"Self-Evolving LLM Agent for Biomedical Research. Autonomous multimodal agent platform from Princeton, Stanford, UCLA. Performs biomedical research tasks without API keys. Published on bioRxiv.","github":"https://github.com/zaixizhang/STELLA","repo":"zaixizhang/STELLA","tags":["biomedical","multimodal","self-evolving","Princeton-Stanford"],"category":"medical","homepage":"https://stella-agent.com"},{"name":"ARIS (Auto-Research-In-Sleep)","description":"Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework lock-in — works with Claude Code, Codex, OpenClaw.","github":"https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep","repo":"wanshuiyin/Auto-claude-code-research-in-sleep","tags":["ML-research","paper-review","experiment-automation","idea-generation"],"category":"science","homepage":null},{"name":"Antigravity Awesome Skills","description":"1000+ battle-tested agentic skills for Claude Code, Antigravity, and Cursor. Includes official skills from Anthropic and Vercel. Covers engineering, analysis, and more.","github":"https://github.com/sickn33/antigravity-awesome-skills","repo":"sickn33/antigravity-awesome-skills","tags":["1000+ skills","Claude Code","Antigravity","battle-tested"],"category":"general","homepage":null},{"name":"Awesome Agent Skills","description":"500+ agent skills from official dev teams and community, compatible with Claude Code, Codex, Antigravity, Gemini CLI, Cursor, and more.","github":"https://github.com/VoltAgent/awesome-agent-skills","repo":"VoltAgent/awesome-agent-skills","tags":["500+ skills","cross-platform","official+community","multi-agent"],"category":"general","homepage":null},{"name":"Claude Skills Collection","description":"192 Claude Code skills and agent plugins for Claude Code, Codex, Gemini CLI, Cursor, and 8+ coding agents. Covers engineering, marketing, product, compliance, and advisory.","github":"https://github.com/alirezarezvani/claude-skills","repo":"alirezarezvani/claude-skills","tags":["192 skills","8+ agents","engineering","multi-domain"],"category":"general","homepage":null},{"name":"Baoyu Skills","description":"Curated collection of high-quality Claude Code skills by Baoyu (宝玉). 9.6K+ stars. Covers coding, writing, research, and productivity workflows.","github":"https://github.com/jimliu/baoyu-skills","repo":"jimliu/baoyu-skills","tags":["curated","high-quality","productivity","Chinese-community"],"category":"general","homepage":null},{"name":"Skills.sh","description":"The Agent Skills Directory by Vercel. 89,000+ skills for 20+ AI agents (Claude Code, Copilot, Cursor, Gemini, Codex). One-command install: npx skills add <repo>.","github":null,"repo":null,"tags":["Vercel","89K+ skills","20+ agents","leaderboard"],"category":"general","homepage":"https://skills.sh"},{"name":"Skills.lc","description":"The open ecosystem for AI agent skills. 250K+ skills with 114M+ installs. Discover, share, and install reusable skills for Claude Code, Codex, Cursor, Windsurf, and Roo Code.","github":"https://github.com/Harries/skills-desktop","repo":"Harries/skills-desktop","tags":["250K+ skills","multi-platform","open-ecosystem"],"category":"general","homepage":"https://skills.lc/"},{"name":"AIPOCH Medical Research Skills","description":"200+ medical research skills covering Evidence Insights, Protocol Design, Data Analysis (R/Python bioinformatics, statistical modeling, ML pipelines), and Academic Writing. One-click OpenClaw install script.","github":"https://github.com/aipoch/medical-research-skills","repo":"aipoch/medical-research-skills","tags":["medical","bioinformatics","protocol-design","statistical-modeling","X-recommended"],"category":"research","homepage":"https://github.com/aipoch/medical-research-skills"},{"name":"OpenClaw Master Skills","description":"339+ curated best skills, weekly updated from ClawHub + GitHub + community. Includes academic-deep-research, data-analysis, perplexity search, and more. Install via clawhub install.","github":"https://github.com/LeoYeAI/openclaw-master-skills","repo":"LeoYeAI/openclaw-master-skills","tags":["curated","weekly-updated","data-analytics","deep-research","X-recommended"],"category":"general","homepage":"https://github.com/LeoYeAI/openclaw-master-skills"},{"name":"AMiner Open Skill","description":"Academic literature search skill powered by AMiner. 28 APIs + 6 workflows for scholar/paper/institution/journal/patent queries. Natural language search like \"latest advances in Transformers\".","github":"https://github.com/CanXiangCC/aminer-open-skill","repo":"CanXiangCC/aminer-open-skill","tags":["AMiner","scholar-search","paper-search","citation-network","X-recommended"],"category":"research","homepage":"https://github.com/CanXiangCC/aminer-open-skill"},{"name":"Research-Claw Plugins","description":"350+ academic research skills, MCP configs, and plugins for Research-Claw and AI agents. Covers literature review, paper writing, experiment tracking, and more.","github":"https://github.com/wentorai/research-plugins","repo":"wentorai/research-plugins","tags":["350+ skills","MCP","academic","Research-Claw"],"category":"research","homepage":null},{"name":"OmicSkills","description":"Skill library for bioinformatics and multi-omics workflows. Organized by top-level omics categories to reduce complexity and attention fragmentation. Built on BioClaw skills. Community-driven, open for contributions.","github":"https://github.com/zongtingwei/Omicskills","repo":"zongtingwei/Omicskills","tags":["multi-omics","bioinformatics","BioClaw-based","community"],"category":"research","homepage":null},{"name":"bioSkills","description":"A set of SKILLS.md for doing bioinformatics with agents like Claude Code. Curated bioinformatics skill templates ready to drop into your agent workflow.","github":"https://github.com/GPTomics/bioSkills","repo":"GPTomics/bioSkills","tags":["bioinformatics","Claude Code","SKILLS.md","GPTomics"],"category":"science","homepage":null},{"name":"OpenBioMed Skills","description":"45 skills for biomedical research and drug discovery. Covers drug discovery, protein analysis & engineering, and single-cell omics. By PharMolix + Tsinghua AIR.","github":"https://github.com/PharMolix/OpenBioMed","repo":"PharMolix/OpenBioMed","tags":["45 skills","drug-discovery","protein-engineering","single-cell","Tsinghua-AIR"],"category":"medical","homepage":null},{"name":"SciAgent-Skills","description":"196 ready-to-use scientific skills covering genomics, proteomics, drug discovery, biostatistics, scientific computing, and writing. Supports Claude Code Plugin mode (/plugin install). Pixi-managed environment.","github":"https://github.com/jaechang-hits/SciAgent-Skills","repo":"jaechang-hits/SciAgent-Skills","tags":["196 skills","11 categories","Claude Plugin","life-sciences"],"category":"science","homepage":null},{"name":"Agent Skills Hub","description":"Discover and compare open-source Agent Skills, tools and MCP servers. Quality scoring, trending analysis, automated GitHub sync.","github":"https://github.com/zhuyansen/agent-skills-hub","repo":"zhuyansen/agent-skills-hub","tags":["quality-scoring","trending","MCP","aggregator"],"category":"general","homepage":"https://agentskillshub.top"},{"name":"YAO Meta Skill","description":"Skill quality management framework — create, evaluate, package, and govern reusable agent skills. Zero-cost static checks + LLM-based blind eval.","github":"https://github.com/yaojingang/yao-meta-skill","repo":"yaojingang/yao-meta-skill","tags":["quality-framework","governance","evaluation","packaging"],"category":"research","homepage":"https://github.com/yaojingang/yao-meta-skill"},{"name":"Nobel Medicine Minds","description":"Cognitive frameworks of 52 Nobel Medicine laureates (2004–2025), distilled into runnable SKILL.md files. Each laureate gets a thinking model, evidence, and application guide — from Karikó's anti-consensus persistence to Yamanaka's reprogramming intuition.","github":"https://github.com/ChrisLou-bioinfo/nobel-medicine-minds","repo":"ChrisLou-bioinfo/nobel-medicine-minds","tags":["Nobel Prize","cognitive-distillation","thinking-frameworks","education"],"category":"science","homepage":null},{"name":"Humanizer","description":"Claude Code skill that removes signs of AI-generated writing from text. Makes academic prose sound natural and human-written. 12.8K stars.","github":"https://github.com/blader/humanizer","repo":"blader/humanizer","tags":["writing","AI-detection","humanize","12.8K stars"],"category":"science","homepage":null},{"name":"Research Paper Writing Skills","description":"Skill package for ML/CV/NLP paper writing. Write or rewrite Abstract, Introduction, Methods, Experiments, Conclusion. Claim-evidence alignment, reviewer self-audit. Adapted from Prof. Peng Sida's notes.","github":"https://github.com/Master-cai/Research-Paper-Writing-Skills","repo":"Master-cai/Research-Paper-Writing-Skills","tags":["paper-writing","ML/CV/NLP","academic","1.1K stars"],"category":"science","homepage":null},{"name":"Awesome AI Research Writing","description":"Curated prompts and agent skills for AI-assisted research writing. Translation, polishing, analysis, and more. Practical templates for every stage of paper preparation. 16.3K stars.","github":"https://github.com/Leey21/awesome-ai-research-writing","repo":"Leey21/awesome-ai-research-writing","tags":["writing","translation","polishing","prompts","16.3K stars"],"category":"science","homepage":null},{"name":"Paper Orchestra Skills","description":"7-skill pipeline for automated research paper writing based on arXiv:2604.05018 (Harvard/Google). Outline → Plotting → Literature Review → Section Writing → Content Refinement + Benchmark. No API keys, no SDK — pure skill instructions + deterministic helpers. Works with any coding agent.","github":"https://github.com/Ar9av/paper-orchestra","repo":"Ar9av/paper-orchestra","tags":["paper-writing","multi-agent-pipeline","LaTeX","arXiv-paper","no-API-keys"],"category":"science","homepage":null},{"name":"Bioinformatics God Skill","description":"Collective cognitive OS from 50 top bioinformatics scholars. 7 mental models, 10 decision heuristics, 6 school-of-thought tensions. 970 lines of research + 389 lines of dialogue analysis. Covers genomics, single-cell, structural biology, cancer genomics, systems biology, microbiome. By zwbao.","github":"https://github.com/zwbao/bioinformatics-god-skill","repo":"zwbao/bioinformatics-god-skill","tags":["cognitive-distillation","bioinformatics","50-scholars","thinking-frameworks"],"category":"science","homepage":null}],"meta":{"total_projects":143,"total_skills":19,"total_skill_hubs":34,"project_categories":{"core":"Core Platform & Lightweight Variants","team":"Team & Orchestration","science":"Medical & Clinical (Biomedicine)","bio-omics":"Bioinformatics & Omics (Biomedicine)","drug-molecular":"Drug Discovery & Molecular (Biomedicine)","general-research":"Autonomous End-to-End Research","specialized":"Personal Research Workbench","paper-tools":"Paper & Literature Tools","education":"Education","benchmark":"Benchmarks & Evaluation","security":"Security"},"skill_hub_categories":{"registry":"Official Registries","science":"Scientific & Research Skills","medical":"Medical & Biomedical Skills","research":"Research & Domain-Specific","general":"General Collections"},"total_project_categories":11,"total_survey_skills":2203,"total_skill_categories":34,"api_version":"1.1","source":"https://claw4science.org"}}