# Claw4Science

> Curated directory of AI agent projects and skill libraries for scientific research, bioinformatics, and biomedicine.

## Website
- Homepage: https://claw4science.org/
- Skills Directory: https://claw4science.org/skills
- Skill Hubs: https://claw4science.org/skill-hubs
- Skill Search: https://claw4science.org/ai-search
- Blog: https://claw4science.org/blog
- Contribute: https://claw4science.org/contribute
- About: https://claw4science.org/about
- Developers: https://claw4science.org/developers
- API: https://claw4science.org/api/projects
- Same-name Projects: https://claw4science.org/samename

## Projects (149+ total)

### Core Platform & Lightweight Variants
- [OpenClaw](https://github.com/openclaw/openclaw): The core platform. Personal AI assistant connecting 20+ messaging apps (WhatsApp, Telegram, Slack, Discord, Signal, iMessage, Teams, Matrix, Feishu, L
- [NanoBot](https://github.com/HKUDS/nanobot): Ultra-lightweight OpenClaw in Python. 99% less code, full agent capabilities. Supports MCP, multi-model (OpenAI, Anthropic, Gemini, Ollama), memory, c
- [PicoClaw](https://github.com/sipeed/picoclaw): Tiny, fast, and deployable anywhere. Ultra-efficient AI assistant written in Go by Sipeed. Designed for edge devices and resource-constrained environm
- [MicroClaw](https://github.com/microclaw/microclaw): 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
- [ZeroClaw](https://github.com/zeroclaw-labs/zeroclaw): Fast, small, and fully autonomous AI assistant infrastructure. Deploy anywhere, swap anything. Written in Rust with extreme performance focus — the in
- [NanoClaw](https://github.com/qwibitai/nanoclaw): Lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail. Built on Anthropic Ag
- [EdgeClaw](https://github.com/Openbmb/EdgeClaw): Edge-Cloud Collaborative AI Agent built on OpenClaw — bringing the Claude Code experience to open source. v2.0 features ClawXMemory (multi-layered str
- [PythonClaw](https://github.com/ericwang915/PythonClaw): OpenClaw reimagined in pure Python. Autonomous AI agent with memory, RAG, skills, web dashboard, voice input, and multi-channel support (Telegram, etc
- [IronClaw](https://github.com/nearai/ironclaw): Rust implementation of OpenClaw focused on privacy and security. Memory-safe architecture with Rust's ownership model, built by NEAR AI. Ideal for sen
- [NullClaw](https://github.com/nullclaw/nullclaw): Fastest, smallest, fully autonomous AI assistant infrastructure written in Zig. Part of the Null ecosystem (NullHub UI, NullWatch observability, NullT
- [FastClaw](https://github.com/fastclaw-ai/fastclaw): Faster and lighter OpenClaw alternative written in Go. Focused on speed, simplicity, and low resource usage. Quick to deploy for researchers who want 
- [Hermes Agent](https://github.com/NousResearch/hermes-agent): The self-improving AI agent by Nous Research. Built-in learning loop — creates skills from experience, improves during use, persists knowledge across 
- [NemoClaw](https://github.com/NVIDIA/NemoClaw): NVIDIA official reference stack for running OpenClaw securely inside NVIDIA OpenShell sandbox. Managed inference with Nemotron open-source models. Ess
- [OpenHarness](https://github.com/HKUDS/OpenHarness): Open Agent Harness from HKUDS (NanoBot team). Runtime environment and execution framework for AI agents. 615 stars in 1 day.
- [autoagent](https://github.com/kevinrgu/autoagent): Autonomous harness engineering. Self-configuring agent runtime that adapts to your workflow. 560 stars in 24 hours.

### Team & Orchestration
- [Clawith](https://github.com/dataelement/Clawith): OpenClaw for Teams. Multi-agent collaboration with persistent identity, long-term memory, and autonomous 'Aware' consciousness system. 6 trigger types
- [MetaClaw](https://github.com/aiming-lab/MetaClaw): Self-learning agent that evolves from every conversation. LoRA-based continual learning + reinforcement learning, no GPU cluster needed. Supports Open
- [ClawX](https://github.com/ValueCell-ai/ClawX): Desktop app providing a graphical interface for OpenClaw AI agents. Turns CLI-based AI orchestration into a visual desktop experience without using th
- [ArgusBot](https://github.com/waltstephen/ArgusBot): 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 over
- [TinyAGI](https://github.com/TinyAGI/tinyclaw): Agent teams orchestrator for One Person Company. Coordinate multiple specialized agents for solo founders and indie researchers. Formerly TinyClaw.
- [HiClaw](https://github.com/alibaba/hiclaw): Collaborative Multi-Agent OS by Alibaba. Transparent, human-in-the-loop task coordination via Matrix rooms. Open-source agent team orchestration for e
- [OpenSpace](https://github.com/HKUDS/OpenSpace): Agent optimization framework from HKUDS (NanoBot team). Makes agents smarter, lower-cost, and self-evolving. Useful for improving any science agent's 
- [Edict](https://github.com/cft0808/edict): Multi-agent orchestration inspired by China's Imperial Three Departments and Six Ministries system. 9 specialized AI agents with real-time dashboard, 
- [ClawTeam](https://github.com/HKUDS/ClawTeam): Agent Swarm Intelligence — one command, full automation. Agents spawn swarms, delegate tasks, and deliver results. Supports Claude Code, Codex, OpenCl
- [ClawTeam-OpenClaw](https://github.com/win4r/ClawTeam-OpenClaw): ClawTeam fork with deep OpenClaw integration. Default openclaw agent, per-agent session isolation, exec approval auto-config, production-hardened spaw
- [ClawManager](https://github.com/Yuan-lab-LLM/ClawManager): Kubernetes-first control plane for managing OpenClaw and Linux desktop runtimes at team and cluster scale. Web UI for multi-instance orchestration.
- [MagiClaw](https://github.com/sjtu-sai-agents/MagiClaw): Conversational command center for scientific agent teams. From SJTU SAI Agents. Orchestrate multiple research agents through natural language dialogue
- [AlphaClaw](https://github.com/chrysb/alphaclaw): The ultimate OpenClaw harness. Browser-based setup wizard, self-healing watchdog, Git-backed rollback, multi-agent management, prompt hardening, and o
- [Open Multi-Agent](https://github.com/JackChen-me/open-multi-agent): TypeScript multi-agent framework. One runTeam() call from goal to result. Auto task decomposition, parallel execution. 3 dependencies, deploys anywher
- [Multica](https://github.com/multica-ai/multica): Open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills. Agents show up on boards,

### Biomedicine & Life Sciences
- [EvoScientist](https://github.com/EvoScientist/EvoScientist): Self-evolving multi-agent AI research system. 6 sub-agents (plan, research, code, debug, analyze, write) for end-to-end scientific discovery. #1 on De
- [MedgeClaw](https://github.com/xjtulyc/MedgeClaw): AI research assistant for biomedicine built on Claude Code with 140 K-Dense scientific skills. Real-time research dashboard, RStudio (:8787), JupyterL
- [OmicsClaw](https://github.com/TianGzlab/OmicsClaw): Multi-omics AI analysis tool from TianGz Lab. Focused on genomics, transcriptomics, and proteomics data processing with intelligent agent workflows.
- [LabClaw](https://github.com/wu-yc/LabClaw): Operating layer for LabOS — Stanford-Princeton AI Co-Scientists project. Automated scientific co-discovery workflows for laboratory research.
- [MedClaw (zteyesreal)](https://github.com/zteyesreal/medclaw): Early-stage medical AI project exploring agent-based approaches for clinical decision support and medical data analysis.
- [ClawBio](https://github.com/ClawBio/ClawBio): The first bioinformatics-native AI agent skill library. Local-first, reproducible, built on OpenClaw. Covers genomics, population genetics, and equity
- [BioClaw](https://github.com/Runchuan-BU/BioClaw): AI-powered bioinformatics research assistant built on OpenClaw. Integrates PubMed literature search and PyMOL molecular visualization for streamlined 
- [MolClaw](https://github.com/IDEA-XL/MolClaw): Light, practical, memory-enabled AI orchestrator for science. Built on NanoClaw. Adds OpenAI/OpenRouter providers, Discord/WhatsApp channels, runtime 
- [MedClaw (Paulzhang)](https://github.com/Paulzhang2023/medclaw): Medical-domain OpenClaw customization. Tailored for clinical and healthcare AI agent workflows. Chinese-language focused.
- [STELLA](https://github.com/zaixizhang/STELLA): Self-evolving multimodal agent platform for biomedical research. From Princeton/Stanford/UCLA. Published on bioRxiv and arXiv. Live demo at stella-age
- [HealthClaw](https://github.com/HC-Guo/HealthClaw): Open-source self-evolving personal health copilot. Medical consultation support, meal planning, report interpretation, chronic-care follow-up, wearabl

### Bioinformatics & Omics
- [PopGenAgent](https://github.com/ai4nucleome/POPGENAGENT): Tool-aware, reproducible, report-oriented AI workflows for population genomics. Template-driven execution with publication-quality figures, full prove
- [CARIBOU](https://github.com/OpenTechBio/CARIBOU): Computational AI Research Interface for Bioinformatics, Omics, and Unifying Agents. Multi-agent bioinformatics system by OpenTechBio.
- [AutoBA](https://github.com/JoshuaChou2018/AutoBA): An AI agent for fully automated multi-omic analyses. Supports RNA-seq, scRNA-seq, spatial transcriptomics, WGS/WES, and ChIP-seq with automated code r
- [SpatialAgent](https://github.com/Genentech/SpatialAgent): An AI agent for spatial biology by Genentech. Processes multimodal spatial genomics data for research insights.
- [CRISPR-GPT](https://github.com/cong-lab/crispr-gpt-pub): LLM agent for CRISPR genome engineering. Assists with guide RNA design, experiment planning, and protocol optimization.
- [BioMaster](https://github.com/ai4nucleome/BioMaster): AI agent system for various bioinformatics tasks with specialized agent coordination. From the same group as POPGENAGENT.
- [CellVoyager](https://github.com/zou-group/CellVoyager): AI CompBio agent that autonomously analyzes biological data and generates new insights. From Stanford Zou Group. Published in Nature Methods. Speciali
- [OpenLife](https://github.com/AndyZhuang/OpenLife): Claw-like Agent for bioinformatics research. Lightweight, Python-based assistant for computational biology workflows.
- [Biomni](https://github.com/snap-stanford/biomni): General-purpose biomedical AI agent from Stanford SNAP Lab. Broad coverage across biomedical tasks with a unified agent architecture.
- [BioOS-Claws](https://github.com/GBA-BI/BioOS-Claws): BioOS platform integration for OpenClaw agents. JavaScript-based, actively developed.
- [EpiClaw](https://github.com/GBA-BI/EpiClaw): Epidemiology AI agent from GBA-BI. Extends OpenClaw with epidemic prevention, early warning, epidemiological analysis, and BioOS integration.
- [PantheonOS](https://github.com/aristoteleo/PantheonOS): Evolvable, distributed agent framework for data science from the dynamo/Spateo team. Specialized in single-cell and spatial transcriptomics workflows.
- [OmicClaw](https://github.com/Starlitnightly/omicclaw): OmicVerse agent skill. Connects the OmicVerse computational biology framework to OpenClaw agents.
- [autoBioResearch](https://github.com/JMGamma/autoBioResearch): Autonomous biological knowledge graph builder. Searches PubMed and Semantic Scholar, extracts entities/interactions with LLM, stores in SQLite, detect
- [NeuroClaw](https://github.com/CUHK-AIM-Group/NeuroClaw): Neuroscience AI agent from CUHK AIM Group. Early stage — no description yet, actively developed.
- [BioMedAgent](https://github.com/BOBQWERA/BioMedAgent): Biomedical AI agent published in Nature Biomedical Engineering. Dormant since Feb 2025 but with top-tier publication backing.

### Drug Discovery & Molecular
- [AIAgents4Pharma](https://github.com/VirtualPatientEngine/AIAgents4Pharma): Multi-agent platform for pharmaceutical R&D. Covers drug discovery, drug development, and clinical pipeline automation. Built by VirtualPatientEngine.
- [ChemGraph](https://github.com/argonne-lcf/ChemGraph): Agentic framework for computational chemistry and materials science workflows. From Argonne National Laboratory (ALCF). Orchestrates chemistry simulat
- [Virtual Lab](https://github.com/zou-group/virtual-lab): A virtual lab of LLM agents for science research. Multi-agent system for nanobody design with principal investigator agent coordination.
- [MDCrow](https://github.com/ur-whitelab/MDCrow): Molecular dynamics simulations with an LLM agent. Automates simulation setup, execution, and analysis using natural language.
- [DrugClaw (QSong)](https://github.com/QSong-github/DrugClaw): Agentic RAG for drug intelligence: 57 skills, 15 task categories — DTI, ADR, DDI, pharmacogenomics, repurposing. Powered by LangGraph.
- [DrugClaw (DrugClaw)](https://github.com/DrugClaw/DrugClaw): AI Research Assistant for Accelerated Drug Discovery. Built with Rust for high performance. Covers compound screening, ADMET prediction, and lead opti
- [ChemClaw](https://github.com/AI4Chem/ChemClaw): Curated skills package for chemistry-focused AI workflows. Installable modularly via npx with stable and experimental skill tiers.
- [OriGene](https://github.com/GENTEL-lab/OriGene): Self-evolving virtual disease biologist for mechanism-guided therapeutic target discovery. Automates disease mechanism analysis and drug target identi
- [ChemCrow](https://github.com/ur-whitelab/chemcrow-public): Pioneering chemistry AI agent (2023) from ur-whitelab. LangChain-based, cited in official docs. The foundational project that inspired MDCrow and the 
- [TCM-Agent](https://github.com/AITCM/TCM-Agent): LLM-powered multi-agent system for Traditional Chinese Medicine network pharmacology. Compound query (PubChem), target analysis (TTD), molecular simil
- [PyMolClaw](https://github.com/junior1p/PyMolClaw): Molecular visualization skill powered by PyMOL. Natural language → publication-quality figures. 13 scripts: structure alignment, binding sites, Goodse
- [BloClaw](https://github.com/qinheming/BIoClaw): Omniscient multi-modal agentic workspace for scientific discovery. Cheminformatics (RDKit), protein folding (ESMFold), molecular docking, autonomous R

### General Research & Automation
- [RD-Agent](https://github.com/microsoft/RD-Agent): Microsoft R&D automation platform. AI-driven data and model research — automates hypothesis generation, experiment design, and iterative improvement f
- [AI-Scientist-v2](https://github.com/SakanaAI/AI-Scientist-v2): Workshop-level automated scientific discovery via agentic tree search. By Sakana AI. Autonomously generates research papers through iterative hypothes
- [DATAGEN](https://github.com/starpig1129/DATAGEN): AI-driven multi-agent research assistant automating hypothesis generation, data analysis, and report writing. Full research pipeline from question to 
- [OpenAGS](https://github.com/openags/OpenAGS): Autonomous Generalist Scientist — AI agent targeting all scientific fields. Broad-scope autonomous research from hypothesis to verification.
- [Open Co-Scientist](https://github.com/jataware/open-coscientist): Open-source adaptation of Google DeepMind's AI Co-Scientist. Generates, reviews, ranks, and evolves research hypotheses using multi-agent architecture
- [AI-Researcher](https://github.com/HKUDS/AI-Researcher): Autonomous scientific innovation system from HKUDS. NeurIPS 2025 paper. End-to-end research automation: literature review, hypothesis generation, expe
- [MedClaw (Suzano)](https://github.com/suzano-ai/medclaw): Universal framework for domain-specific AI agents covering Medical, Legal, Finance, and Sports. Multi-domain architecture with shared agent infrastruc
- [EurekaClaw](https://github.com/EurekaClaw/EurekaClaw): Self-evolving AI research agent by the EurekaClaw team. Autonomous scientific discovery with persistent memory and tool-use capabilities.
- [OpenCLAW Research Platform](https://github.com/Agnuxo1/OpenCLAW-Autonomous-Multi-Agent-Scientific-Research-Platform): Autonomous multi-agent scientific research platform built on OpenClaw. Vision: a network of specialized AI agents for code, papers, and experiments.
- [InnoClaw](https://github.com/SpectrAI-Initiative/InnoClaw): A self-hostable AI research workspace with grounded chat, paper study tools, and scientific skill execution — all anchored to your local files.
- [Prismer](https://github.com/Prismer-AI/Prismer): Open-source alternative to OpenAI's Prism. Unified platform for AI-powered paper reading, learning, and research knowledge management.
- [NanoResearch](https://github.com/OpenRaiser/NanoResearch): Autonomous AI research assistant built on NanoBot. From idea to paper with automated literature review, experiment design, and writing.
- [autoresearch](https://github.com/karpathy/autoresearch): By Andrej Karpathy. Give an AI agent a small but real LLM training setup and let it experiment autonomously overnight. Single GPU, ~100 experiments/ni
- [DeepResearch](https://github.com/Alibaba-NLP/DeepResearch): 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, Bro
- [AgentLaboratory](https://github.com/SamuelSchmidgall/AgentLaboratory): End-to-end autonomous research workflow: Literature Review → Experimentation → Report Writing. Specialized LLM agents collaborate via arXiv, HuggingFa
- [Auto-Deep-Research](https://github.com/HKUDS/Auto-Deep-Research): Open-source, cost-efficient alternative to OpenAI's Deep Research, built on AutoAgent framework by HKUDS. Universal LLM support (OpenAI, Anthropic, De
- [OpenResearcher](https://github.com/TIGER-AI-Lab/OpenResearcher): 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
- [freephdlabor](https://github.com/ltjed/freephdlabor): Personalized multi-agent system that researches 24/7 on your scientific problem. From hypothesis generation through experimentation to publication-rea
- [OmniScientist](https://github.com/tsinghua-fib-lab/OmniScientist): AI Scientist Ecosystem by Tsinghua FIB Lab and Zhongguancun Academy. 7 core papers covering co-evolving ecosystem, expert knowledge integration, high-
- [NeuriCo](https://github.com/ChicagoHAI/NeuriCo): Autonomous research framework from University of Chicago Human+AI Lab. Input a title, domain, and hypothesis — agents handle literature review, experi

### Specialized & Domain-Specific
- [OpenLens AI](https://github.com/jarrycyx/openlens-ai): Fully autonomous multimodal research agent. Combines vision and text understanding for scientific discovery. Chinese academic origin with bilingual su
- [BioAgents](https://github.com/bio-xyz/BioAgents): AI scientist framework for autonomous deep research in biological sciences. Multi-agent system combining literature analysis with data scientist agent
- [SR-Scientist](https://github.com/GAIR-NLP/SR-Scientist): Scientific equation discovery with agentic AI. Published at ICLR 2026. Symbolic regression via AI agents from GAIR Lab (Shanghai Jiao Tong University)
- [BioDiscoveryAgent](https://github.com/snap-stanford/BioDiscoveryAgent): LLM-based AI agent for closed-loop design of genetic perturbation experiments. Autonomous reasoning for biological discovery.
- [GeneClaw](https://github.com/Clawland-AI/Geneclaw): Self-evolving AI agent framework with 5-layer safety gatekeeper. Agents observe failures, propose fixes, and safely apply them. Built on HKUDS/nanobot
- [Dr. Claw](https://github.com/OpenLAIR/dr-claw): AI Research IDE with built-in "AI Doctors" assistants. Full research lifecycle: Survey → Ideation → Experiment → Publication → Promotion. 100+ researc
- [ScienceClaw (Zaoqu-Liu)](https://github.com/Zaoqu-Liu/ScienceClaw): AI Research Lab That Never Sleeps. 9 agents, 263 skills, 77 databases — from literature to publication, every discipline, zero boundaries. Full resear
- [ScienceClaw (TaichuAI)](https://github.com/AgentTeam-TaichuAI/ScienceClaw): Personal research assistant built with LangChain DeepAgents and AIO Sandbox. A new architecture beyond OpenClaw, offering stronger security, better tr
- [ScienceClaw (beita6969)](https://github.com/beita6969/ScienceClaw): Self-evolving AI research colleague. 285 skills that grow at runtime — the agent writes new skills based on your usage patterns. 4-layer persistent me
- [SciClaw (drpedapati)](https://github.com/drpedapati/sciclaw): Paired-scientist AI assistant for reproducible research. Lightweight Go runtime, lifecycle hooks, manuscript integration, 12 baseline scientific skill
- [SciClaw (nahisaho)](https://github.com/nahisaho/sciclaw): AI research assistant with Docker sandbox agents. Isolated execution environment for safe, reproducible scientific computing workflows.
- [ScienceClaw (MIT LAMM)](https://github.com/lamm-mit/scienceclaw): Open-source AI agent swarm for crowdsourced scientific discovery. 300+ interoperable tools, plannerless ArtifactReactor coordination, DAG lineage trac
- [DrClaw (InternScience)](https://github.com/InternScience/DrClaw): 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 th
- [MatClaw](https://github.com/DingyangLyu/MatClaw): Open materials-science agent that turns natural-language tasks into reproducible simulation workflows.
- [ARIS](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep): Auto-Research-In-Sleep — let Claude Code do research while you sleep. Lightweight Markdown-only skills for autonomous ML research: cross-model review 
- [CodeScientist](https://github.com/allenai/codescientist): Automated scientific discovery system by Allen AI. LLM-as-a-mutator generates experiment ideas from paper+code combinations, then creates, runs, and d
- [Memento-Skills](https://github.com/Memento-Teams/Memento-Skills): Let Agents Design Agents. A meta-framework where AI agents create, test, and evolve new skills and agents autonomously. Unlike traditional skill libra
- [DeepScientist](https://github.com/ResearAI/DeepScientist): Local-first AI research studio. 15-minute setup, one repo per research quest, visible progress, human takeover anytime. Published at ICLR 2026.
- [StatsClaw](https://github.com/statsclaw/statsclaw): Multi-agent workflow for statistical software development. Information-isolated agents: builder (no ground truth), simulator (no algorithm), tester (i

### Paper & Writing Tools
- [AutoResearchClaw](https://github.com/aiming-lab/AutoResearchClaw): Fully autonomous, self-evolving research framework: from a one-line idea to a conference-level paper. 23-stage pipeline with multi-agent debate, self-
- [RS-PaperClaw](https://github.com/thinson/RS-PaperClaw): Auto-tracks, auto-analyzes, and auto-digests remote sensing papers. Stop reading remote sensing papers manually.
- [PaperClaw (AkaliKong)](https://github.com/AkaliKong/PaperClaw): Agent-orchestrated pipeline that automates the full academic research lifecycle — from arXiv search and relevance scoring to deep reading, code evalua
- [paper_claw (PigeonDan1)](https://github.com/PigeonDan1/paper_claw): Personalized daily research digests from arXiv and beyond. Customizable categories, intelligent classification, and agent-based multilingual summaries
- [Research-Claw](https://github.com/wentorai/Research-Claw): Full-stack AI research assistant — "In the AI era, why can't everyone be a PI?" Supports extensible skills, literature review, note-taking, experiment
- [ResearchClaw (ymx10086)](https://github.com/ymx10086/ResearchClaw): Personal AI assistant built for research. Fast setup, local or cloud, integrates with chat apps. Streamlines literature review, note-taking, experimen
- [CitationClaw](https://github.com/VisionXLab/CitationClaw): Turning every citation into explainable impact. Citation analysis and impact assessment tool for academic research — tracks citation networks, measure
- [PaperClaw (guhaohao0991)](https://github.com/guhaohao0991/PaperClaw): OpenClaw skill for paper search-review-critique expert-agent. Generates research workflows for specific topics (demo: Scientific ML and 3D geometry).
- [ClawPhD](https://github.com/ZhihaoAIRobotic/ClawPhD): Agent that turns academic papers into publication-ready diagrams, posters, videos, and more. Visual research communication tool — automates the creati
- [PaperClaw (meowscles69)](https://github.com/meowscles69/PaperClaw): 27 OpenClaw skills for academic research teams — literature reviews, hypothesis versioning, grant writing, lab knowledge handoffs.
- [ResearchClaw (Noietch)](https://github.com/Noietch/ResearchClaw): Standalone Electron desktop app combining AI-powered paper management, interactive reading notes, and research idea generation — no browser or server 
- [PaperClaw (0xMerl99)](https://github.com/0xMerl99/PaperClaw): Production-ready library of 27 OpenClaw skills for research teams — literature management, synthesis, collaboration, manuscript output, and tracking w
- [research-claw (nanoAgentTeam)](https://github.com/nanoAgentTeam/research-claw): Self-hosted AI assistant for academic research — manages papers, searches literature, tracks deadlines.
- [PaperClaw (1692775560)](https://github.com/1692775560/PaperClaw): High-agency AI automation for academic researchers. Three-layer architecture: LLM decision engine, skill execution layer, and memory knowledge managem

### Education
- [OpenMAIC](https://github.com/THU-MAIC/OpenMAIC): Open Multi-Agent Interactive Classroom by Tsinghua University. One-click immersive AI classroom with AI teachers and peers. Slides, quizzes, whiteboar
- [MathClaw](https://github.com/MathClaw-ruc/MathClaw): Multimodal math learning assistant for middle and high school. Solving workspace, weakness diagnosis, knowledge graphs, error graphs, auto-summaries. 

### Benchmarks & Evaluation
- [ResearchClawBench](https://github.com/InternScience/ResearchClawBench): Benchmark for evaluating whether AI agents can independently conduct scientific research. 40 real-science tasks across 10 disciplines (Astronomy, Chem
- [PinchBench](https://github.com/pinchbench/skill): Real-world benchmarks for AI coding agents. 23 tasks across productivity, research, writing, coding, analysis, email, memory, and skills. Public leade
- [HeurekaBench](https://github.com/mlbio-epfl/HeurekaBench): ICLR 2026 framework to create benchmarks and evaluate AI co-scientists in experimental data-driven scientific research. From EPFL Machine Learning & B
- [ClawSafety (Benchmark)](https://github.com/weibowen555/ClawSafety): Safety benchmark for personal AI agents under realistic prompt injection. 120 adversarial test cases across 5 harm domains, 3 attack vectors, and 5 ha
- [Claw-Eval](https://github.com/claw-eval/claw-eval): End-to-end evaluation suite for autonomous agents. 300 human-verified tasks across 9 categories (service orchestration, multimodal perception, multi-t
- [BioAgent Bench](https://github.com/bioagent-bench/bioagent-bench): AI agent evaluation suite for bioinformatics. Benchmarks LLM agents on real bioinformatics tasks. Covers sequence analysis, genomics workflows, and co

### Security
- [ClawKeeper](https://github.com/rad-security/clawkeeper): Security scanner for AI agent hosts. 42 checks across 5 phases: host hardening, network, prerequisites, installation, security audit. Auto-fix for fir
- [ClawSafety (Scanner)](https://github.com/relaxcloud-cn/clawsafety): Security scanner for Agent Skills — the npm audit for the Agent-Native ecosystem. Scans for shell injection, hardcoded secrets, unpinned dependencies,

## Skill Hubs (32 registries)

- [Anthropic Skills](https://github.com/anthropics/skills): Official Agent Skills repository by Anthropic. The canonical source for Claude Code skills — community contributions, cu
- [ClawHub](https://github.com/openclaw/clawhub): The official OpenClaw skill registry. Publish, version, search, and install text-based agent skills. 6,300+ skills with 
- ClawHub China Mirror: Official ClawHub mirror for mainland China. Same 6,300+ skills, accelerated access without VPN. Full registry sync, sear
- [Awesome OpenClaw Skills](https://github.com/VoltAgent/awesome-openclaw-skills): 5,400+ community skills filtered and categorized from the official Skills Registry. Install via clawhub install <slug> o
- [K-Dense Scientific Skills](https://github.com/K-Dense-AI/claude-scientific-skills): 170+ ready-to-use skills across 17 scientific domains: bioinformatics, cheminformatics, proteomics, clinical research, m
- [AI Research Skills](https://github.com/Orchestra-Research/AI-Research-SKILLs): 86 skills across 22 categories for autonomous AI research. Covers ideation, ML paper writing, fine-tuning, distributed t
- [Academic Research Skills](https://github.com/Imbad0202/academic-research-skills): Full academic pipeline: 13-agent deep research team, 12-agent paper writing (LaTeX/DOCX/MD), multi-perspective peer revi
- [OpenClaw Medical Skills](https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills): The largest open-source medical AI skills library. 869 curated skills covering clinical, genomics, drug discovery, bioin
- [ClawBio](https://github.com/ClawBio/ClawBio): Bioinformatics-native AI agent skill library. 24 skills + 8,000 Galaxy tools. Local-first, reproducible. Features pharma
- SkillHub: Tencent official OpenClaw skills community, optimized for Chinese users. Browse, share, and install curated AI agent ski
- [STELLA](https://github.com/zaixizhang/STELLA): Self-Evolving LLM Agent for Biomedical Research. Autonomous multimodal agent platform from Princeton, Stanford, UCLA. Pe
- [ARIS (Auto-Research-In-Sleep)](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep): Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment au
- [Antigravity Awesome Skills](https://github.com/sickn33/antigravity-awesome-skills): 1000+ battle-tested agentic skills for Claude Code, Antigravity, and Cursor. Includes official skills from Anthropic and
- [Awesome Agent Skills](https://github.com/VoltAgent/awesome-agent-skills): 500+ agent skills from official dev teams and community, compatible with Claude Code, Codex, Antigravity, Gemini CLI, Cu
- [Claude Skills Collection](https://github.com/alirezarezvani/claude-skills): 192 Claude Code skills and agent plugins for Claude Code, Codex, Gemini CLI, Cursor, and 8+ coding agents. Covers engine
- [Baoyu Skills](https://github.com/jimliu/baoyu-skills): Curated collection of high-quality Claude Code skills by Baoyu (宝玉). 9.6K+ stars. Covers coding, writing, research, and 
- Skills.sh: The Agent Skills Directory by Vercel. 89,000+ skills for 20+ AI agents (Claude Code, Copilot, Cursor, Gemini, Codex). On
- [Skills.lc](https://github.com/Harries/skills-desktop): The open ecosystem for AI agent skills. 250K+ skills with 114M+ installs. Discover, share, and install reusable skills f
- [AIPOCH Medical Research Skills](https://github.com/aipoch/medical-research-skills): 200+ medical research skills covering Evidence Insights, Protocol Design, Data Analysis (R/Python bioinformatics, statis
- [OpenClaw Master Skills](https://github.com/LeoYeAI/openclaw-master-skills): 339+ curated best skills, weekly updated from ClawHub + GitHub + community. Includes academic-deep-research, data-analys
- [AMiner Open Skill](https://github.com/CanXiangCC/aminer-open-skill): Academic literature search skill powered by AMiner. 28 APIs + 6 workflows for scholar/paper/institution/journal/patent q
- [Research-Claw Plugins](https://github.com/wentorai/research-plugins): 350+ academic research skills, MCP configs, and plugins for Research-Claw and AI agents. Covers literature review, paper
- [OmicSkills](https://github.com/zongtingwei/Omicskills): Skill library for bioinformatics and multi-omics workflows. Organized by top-level omics categories to reduce complexity
- [bioSkills](https://github.com/GPTomics/bioSkills): A set of SKILLS.md for doing bioinformatics with agents like Claude Code. Curated bioinformatics skill templates ready t
- [OpenBioMed Skills](https://github.com/PharMolix/OpenBioMed): 45 skills for biomedical research and drug discovery. Covers drug discovery, protein analysis & engineering, and single-
- [SciAgent-Skills](https://github.com/jaechang-hits/SciAgent-Skills): 196 ready-to-use scientific skills covering genomics, proteomics, drug discovery, biostatistics, scientific computing, a
- [Agent Skills Hub](https://github.com/zhuyansen/agent-skills-hub): Discover and compare open-source Agent Skills, tools and MCP servers. Quality scoring, trending analysis, automated GitH
- [YAO Meta Skill](https://github.com/yaojingang/yao-meta-skill): Skill quality management framework — create, evaluate, package, and govern reusable agent skills. Zero-cost static check
- [Nobel Medicine Minds](https://github.com/ChrisLou-bioinfo/nobel-medicine-minds): Cognitive frameworks of 52 Nobel Medicine laureates (2004–2025), distilled into runnable SKILL.md files. Each laureate g
- [Humanizer](https://github.com/blader/humanizer): Claude Code skill that removes signs of AI-generated writing from text. Makes academic prose sound natural and human-wri
- [Research Paper Writing Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills): Skill package for ML/CV/NLP paper writing. Write or rewrite Abstract, Introduction, Methods, Experiments, Conclusion. Cl
- [Awesome AI Research Writing](https://github.com/Leey21/awesome-ai-research-writing): Curated prompts and agent skills for AI-assisted research writing. Translation, polishing, analysis, and more. Practical

## Blog
- Latest posts at https://claw4science.org/blog
- Contribute a post: https://claw4science.org/contribute