README
Awesome-OpenClaw-Research 
Survey Paper Available on Overleaf
We maintain a comprehensive survey paper: OpenClaw Research: A Systematic Survey of Large Language Model Agents in Open Deployment
The paper is actively maintained and updated on a regular basis. We welcome comments, suggestions, and feedback from the community — feel free to leave comments directly on Overleaf or open an issue in this repo. Your input helps us improve the survey!
🦞 OpenClaw launched Nov 2025, hit 200k GitHub stars in 84 days, and surpassed 330k stars by March 2026. This repo collects papers studying or built upon the OpenClaw ecosystem, covering claw learning and evolution, safety and security, social dynamics, infrastructure and systems, and applications in embodied AI, mobile agents, scientific discovery, clinical AI, and beyond. The questions are universal; OpenClaw is the lens.
Table of Contents
- Reading Guide — survey-aligned taxonomy
- Papers — Core of this repo
- Other Resources — SDKs, tools, community, related repos
- Contributing
🧭 Reading Guide
This repository follows the OpenClaw Research taxonomy: instead of grouping work only by task domain, it organizes papers by the main sandbox boundary they relax in open deployment. In this setting, agents may evolve after release, interact with untrusted tools and environments, coexist with open populations of humans and agents, and rely on persistent runtime substrates.
| Principle | Repo Section | Core Question | Typical Topics |
|---|---|---|---|
| Open Policy | Learning and Evolving | How does the agent policy or its surrounding state evolve after deployment? | Memory evolution, skill evolution, RL-based agent learning, population-level co-evolution |
| Open Environment | Safety and Security | How can agents remain safe when tools, resources, and environments are untrusted? | Prompt injection, tool attacks, supply-chain risks, sandboxing, auditing, HITL defense |
| Open Population | Claw Society | What collective behaviors emerge among open populations of agents and humans? | Agent-only communities, social dynamics, consensus hallucination, human-agent collaboration |
| Open Substrate | Infrastructure and Systems | What runtime substrate is needed for persistent, observable, accountable agents? | Agent-as-OS, MCP/tool interoperability, edge deployment, GUI-agent infrastructure, evaluation harnesses |
| Application Layer | Applications | How do the four openness dimensions combine in concrete domains? | Robotics, mobile agents, scientific discovery, healthcare, education, domain-specific agents |
📄 Papers
Open Policy: Learning and Evolving
Component Level
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| MemOS: A Memory OS for AI System | arXiv | 2025.07 |  |  |
| OpenViking: The Context Database for AI Agents | GitHub | 2026.01 |  | |
| Hermes-Agent | GitHub | 2026.03 | | |
| AutoResearchClaw:Chat an Idea. Get a Paper. Autonomous, Collaborative & Self-Evolving. | GitHub | 2026.03 | | |
| ScienceClaw | GitHub / Website | 2026.03 | |  |
| Hierarchical Memory Orchestration for Personalized Persistent Agents | arXiv | 2026.04 | | |
| SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering | arXiv | 2026.04 | | |
Individual Level
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| OpenClaw-RL: Train Any Agent Simply by Talking | arXiv | 2026.03 | | |
| MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild | arXiv | 2026.03 |  | |
| StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning | arXiv | 2026.04 | | |
Population Level
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| SkillClaw: Let Skills Evolve Collectively with Agentic Evolver | arXiv | 2026.04 | | |
| EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale | arXiv | 2026.04 | | |
Open Environment: Safety and Security
Threat Landscape
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent | arXiv | 2026.02 |  | |
| A Trajectory-Based Safety Audit of Clawdbot (OpenClaw) | arXiv | 2026.02 |  | |
| Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw | arXiv | 2026.03 |  | |
| Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats | arXiv | 2026.03 | | |
| Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents | arXiv | 2026.04 | | |
| ClawArena: Benchmarking AI Agents in Evolving Information Environments | arXiv | 2026.04 | | |
| ClawBench: Can AI Agents Complete Everyday Online Tasks? | arXiv | 2026.04 | | |
| Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw | arXiv | 2026.04 |  | |
| ClawLess: A Security Model of AI Agents | arXiv | 2026.04 | | |
Defense Mechanisms
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| Formal Analysis and Supply Chain Security for Agentic AI Skills | arXiv | 2026.02 |  |  |
| Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw | arXiv | 2026.03 | | |
| Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw | arXiv | 2026.03 |  | |
| OpenClaw PRISM: A Zero-Fork, Defense-in-Depth Runtime Security Layer for Tool-Augmented LLM Agents | arXiv | 2026.03 |  | |
| Defensible Design for OpenClaw: Securing Autonomous Tool-Invoking Agents | arXiv | 2026.03 |  | |
Open Population: Claw Society
Emergent Characteristics
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| OpenClaw Agents on Moltbook: Risky Instruction Sharing and Norm Enforcement in an Agent-Only Social Network | arXiv | 2026.02 | | |
| When AI Agents Teach Each Other: Discourse Patterns Resembling Peer Learning in the Moltbook Community | arXiv | 2026.02 |  | |
| OpenClaw AI Agents as Informal Learners at Moltbook: Characterizing an Emergent Learning Community at Scale | arXiv | 2026.02 |  | |
Structural Failures & Design
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| From Agent-Only Social Networks to Autonomous Scientific Research: Lessons from OpenClaw and Moltbook, and the Architecture of ClawdLab and Beach.Science | arXiv | 2026.02 |  |   |
Human–AI Collaboration
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| When Openclaw Agents Learn from Each Other: Insights from Emergent AI Agent Communities for Human-AI Partnership in Education | arXiv | 2026.03 |  | |
Open Substrate: Infrastructure and Systems
Infrastructure of Claw
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem | arXiv | 2026.03 |  | |
| OpenClaw as Language Infrastructure: A Case-Centered Survey of a Public Agent Ecosystem in the Wild (Survey) | Preprints.org | 2026.03 |  | |
Claw as Infrastructure
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers | arXiv | 2026.01 |  | |
| NanoClaw | GitHub | 2026.01 | | |
| PicoClaw: Ultra-Efficient AI Assistant in Go | GitHub | 2026.02 | | |
| Three Provinces and Six Ministries · Edict | GitHub | 2026.02 | | |
| CyberClaw: Next-Gen Transparent Agent Architecture | GitHub | 2026.03 | | |
| ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents | arXiv | 2026.04 |  | |
Applications
Embodied Claws
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks | arXiv | 2026.03 |  | |
| RoboClaw (MINT): Open-Source Embodied Intelligence Assistant | GitHub | 2026.03 | | |
| ROSClaw: An OpenClaw ROS 2 Framework for Agentic Robot Control and Interaction | arXiv | 2026.03 | | |
| RoClaw: The Cerebellum — physical embodiment for AI agents | GitHub | 2026.03 | | |
Mobile Claws
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| StreamingClaw Technical Report | arXiv | 2026.03 | |  |
| UAV-Claw | GitHub | 2026.04 | | |
Scientific Claws
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| From Agent-Only Social Networks to Autonomous Scientific Research: Lessons from OpenClaw and Moltbook, and the Architecture of ClawdLab and Beach.Science | arXiv | 2026.02 | | |
| Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange | arXiv | 2026.03 |  | |
| clawRxiv: Agent-Native Open Research Archive | GitHub / Website | 2026.03 | | |
| AutoResearchClaw:Chat an Idea. Get a Paper. Autonomous, Collaborative & Self-Evolving. | GitHub | 2026.03 | | |
| OpenCLAW-P2P v7.0-P2PCLAW: Resilient Multi-Layer Persistence, Live Reference Verification, and Production-Scale Evaluation of Decentralized AI Peer Review v7.0 -- Mathematical Corrections & Ecosystem Developments Edition | arXiv | 2026.04 | | |
Clinical Claws
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| Autonomous Agent-Orchestrated Digital Twins (AADT): Leveraging the OpenClaw Framework for State Synchronization in Rare Genetic Disorders | arXiv | 2026.03 |  | |
| MedOpenClaw: Auditable Medical Imaging Agents Reasoning over Uncurated Full Studies | arXiv | 2026.03 |  | |
| OpenClaw-Medical-Skills | GitHub | 2026.03 | | |
| When OpenClaw Meets Hospital: Toward an Agentic Operating System for Dynamic Clinical Workflows | arXiv | 2026.03 |  | |
Other Claws
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| DenchClaw | GitHub | 2026.02 | | |
| Scaling Laws for Educational AI Agents | arXiv | 2026.03 |  | |
| MathClaw | GitHub | 2026.03 | | |
- Context Kit — Personal Context Artifacts: 4 Markdown templates (wiki, mental-models, voice, protocols) + 5 Claude Code skills. Solves context amnesia — every session starts context-full. MIT, one-command install.
📦 Other Resources
Official Links
| Name | Link |
|---|---|
| OpenClaw Core | github.com/openclaw/openclaw |
| ClawHub Marketplace | clawhub.com |
| Official Docs | docs.openclaw.ai |
SDKs & Tools
| Name | Language | Description |
|---|---|---|
| openclaw-sdk | Python | Build & publish autonomous AI agents |
| mcp-bridge-openclaw | TypeScript | MCP multi-server bridge |
| amor71/openclaw-mcp | TypeScript | Native MCP client |
| henry-y/openclaw-paper-tools | Python | OpenClaw arXiv paper reader |
Automated Research Tools
| Name | Link | Description |
|---|---|---|
| AutoResearchClaw | GitHub | Fully autonomous 23-stage research pipeline: idea → experiment → conference-ready paper; multi-agent peer review |
| OpenClaw-Medical-Skills | GitHub | 869 curated medical AI skills covering clinical work, genomics, drug discovery & bioinformatics |
| ScienceClaw | GitHub | Autonomous research pipeline; 266+ domain skills; 77+ databases |
| ClawCures | GitHub | AI campaign orchestrator for drug discovery; planner/critic loops; ADMET maps |
| clawRxiv | Website | Academic archive for AI agents — 383 agents, 1,827+ papers; affiliated with Stanford–Princeton Claw4S Conference (deadline Apr 30, 2026, prize $50,200) |
| Claw4Science (Claw4S) | Website | First agent-native scientific conference: submit executable skills, not papers; agent peer review; Stanford–Princeton co-organized |
Security References
Benchmarks
| Name | Link | Description |
|---|---|---|
| PinchBench | pinchbench.com · GitHub | 23 real-world tasks across 8 categories; automated + LLM judge grading |
| EvoClaw | evo-claw.com · HuggingFace | Continuous software evolution benchmark; 7 repos / 5 languages / 98 milestones |
Chinese Community & Tutorials
| Name | Link | Description |
|---|---|---|
| OpenClaw China | BytePioneer-AI/openclaw-china | Domestic IM adaption (3,200+ Stars) |
| 中文教程 | openclawgithub.cc | Config & integration guides |
| Hello Claw | Datawhale | Datawhale tutorial |
| 中文站 | clawcn.net | Domestic LLM guide |
| Learn OpenClaw | learnopenclaw.com | Learning platform |
Related Repositories
Know a great OpenClaw project we missed? Open a PR and help us keep this list growing!
| Repository | Stars | Description |
|---|---|---|
| SamurAIGPT/awesome-openclaw | 823 | Comprehensive list of OpenClaw resources, tools, skills, tutorials & articles |
| mergisi/awesome-openclaw-agents | 830+ | 177 production-ready AI agent templates across 24 categories |
| VoltAgent/awesome-openclaw-skills | — | Community curated skills collection |
| community/openclaw-recipes | — | Common automation recipes |
| templates/claw-templates | — | Starter templates for OpenClaw projects |
| pranciskus/discourse-openclaw | NEW | Discourse forum integration with 12 tools |
| wanikua/ByeByeClaw | NEW | One-command uninstaller for all Claw-family agents |
🤝 Contributing
Contributions are welcome! We especially need help with:
- Papers — Adding missing OpenClaw-related papers with proper links.
- Analysis — Improving paper notes, section placement, and taxonomy alignment.
- Timeline — Updating the ecosystem timeline with new events.
- Resources — Adding useful SDKs, tools, benchmarks, datasets, and community repositories.
Similar repos
README
Awesome-OpenClaw-Research
Survey Paper Available on Overleaf
We maintain a comprehensive survey paper: OpenClaw Research: A Systematic Survey of Large Language Model Agents in Open Deployment
The paper is actively maintained and updated on a regular basis. We welcome comments, suggestions, and feedback from the community — feel free to leave comments directly on Overleaf or open an issue in this repo. Your input helps us improve the survey!
🦞 OpenClaw launched Nov 2025, hit 200k GitHub stars in 84 days, and surpassed 330k stars by March 2026. This repo collects papers studying or built upon the OpenClaw ecosystem, covering claw learning and evolution, safety and security, social dynamics, infrastructure and systems, and applications in embodied AI, mobile agents, scientific discovery, clinical AI, and beyond. The questions are universal; OpenClaw is the lens.
Table of Contents
- Reading Guide — survey-aligned taxonomy
- Papers — Core of this repo
- Other Resources — SDKs, tools, community, related repos
- Contributing
🧭 Reading Guide
This repository follows the OpenClaw Research taxonomy: instead of grouping work only by task domain, it organizes papers by the main sandbox boundary they relax in open deployment. In this setting, agents may evolve after release, interact with untrusted tools and environments, coexist with open populations of humans and agents, and rely on persistent runtime substrates.
| Principle | Repo Section | Core Question | Typical Topics |
|---|---|---|---|
| Open Policy | Learning and Evolving | How does the agent policy or its surrounding state evolve after deployment? | Memory evolution, skill evolution, RL-based agent learning, population-level co-evolution |
| Open Environment | Safety and Security | How can agents remain safe when tools, resources, and environments are untrusted? | Prompt injection, tool attacks, supply-chain risks, sandboxing, auditing, HITL defense |
| Open Population | Claw Society | What collective behaviors emerge among open populations of agents and humans? | Agent-only communities, social dynamics, consensus hallucination, human-agent collaboration |
| Open Substrate | Infrastructure and Systems | What runtime substrate is needed for persistent, observable, accountable agents? | Agent-as-OS, MCP/tool interoperability, edge deployment, GUI-agent infrastructure, evaluation harnesses |
| Application Layer | Applications | How do the four openness dimensions combine in concrete domains? | Robotics, mobile agents, scientific discovery, healthcare, education, domain-specific agents |
📄 Papers
Open Policy: Learning and Evolving
Component Level
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| MemOS: A Memory OS for AI System | arXiv | 2025.07 | | |
| OpenViking: The Context Database for AI Agents | GitHub | 2026.01 | | |
| Hermes-Agent | GitHub | 2026.03 | | |
| AutoResearchClaw:Chat an Idea. Get a Paper. Autonomous, Collaborative & Self-Evolving. | GitHub | 2026.03 | | |
| ScienceClaw | GitHub / Website | 2026.03 | | |
| Hierarchical Memory Orchestration for Personalized Persistent Agents | arXiv | 2026.04 | | |
| SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering | arXiv | 2026.04 | | |
Individual Level
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| OpenClaw-RL: Train Any Agent Simply by Talking | arXiv | 2026.03 | | |
| MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild | arXiv | 2026.03 | | |
| StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning | arXiv | 2026.04 | | |
Population Level
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| SkillClaw: Let Skills Evolve Collectively with Agentic Evolver | arXiv | 2026.04 | | |
| EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale | arXiv | 2026.04 | | |
Open Environment: Safety and Security
Threat Landscape
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent | arXiv | 2026.02 | | |
| A Trajectory-Based Safety Audit of Clawdbot (OpenClaw) | arXiv | 2026.02 | | |
| Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw | arXiv | 2026.03 | | |
| Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats | arXiv | 2026.03 | | |
| Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents | arXiv | 2026.04 | | |
| ClawArena: Benchmarking AI Agents in Evolving Information Environments | arXiv | 2026.04 | | |
| ClawBench: Can AI Agents Complete Everyday Online Tasks? | arXiv | 2026.04 | | |
| Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw | arXiv | 2026.04 | | |
| ClawLess: A Security Model of AI Agents | arXiv | 2026.04 | | |
Defense Mechanisms
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| Formal Analysis and Supply Chain Security for Agentic AI Skills | arXiv | 2026.02 | | |
| Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw | arXiv | 2026.03 | | |
| Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw | arXiv | 2026.03 | | |
| OpenClaw PRISM: A Zero-Fork, Defense-in-Depth Runtime Security Layer for Tool-Augmented LLM Agents | arXiv | 2026.03 | | |
| Defensible Design for OpenClaw: Securing Autonomous Tool-Invoking Agents | arXiv | 2026.03 | | |
Open Population: Claw Society
Emergent Characteristics
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| OpenClaw Agents on Moltbook: Risky Instruction Sharing and Norm Enforcement in an Agent-Only Social Network | arXiv | 2026.02 | | |
| When AI Agents Teach Each Other: Discourse Patterns Resembling Peer Learning in the Moltbook Community | arXiv | 2026.02 | | |
| OpenClaw AI Agents as Informal Learners at Moltbook: Characterizing an Emergent Learning Community at Scale | arXiv | 2026.02 | | |
Structural Failures & Design
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| From Agent-Only Social Networks to Autonomous Scientific Research: Lessons from OpenClaw and Moltbook, and the Architecture of ClawdLab and Beach.Science | arXiv | 2026.02 | | |
Human–AI Collaboration
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| When Openclaw Agents Learn from Each Other: Insights from Emergent AI Agent Communities for Human-AI Partnership in Education | arXiv | 2026.03 | | |
Open Substrate: Infrastructure and Systems
Infrastructure of Claw
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem | arXiv | 2026.03 | | |
| OpenClaw as Language Infrastructure: A Case-Centered Survey of a Public Agent Ecosystem in the Wild (Survey) | Preprints.org | 2026.03 | | |
Claw as Infrastructure
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers | arXiv | 2026.01 | | |
| NanoClaw | GitHub | 2026.01 | | |
| PicoClaw: Ultra-Efficient AI Assistant in Go | GitHub | 2026.02 | | |
| Three Provinces and Six Ministries · Edict | GitHub | 2026.02 | | |
| CyberClaw: Next-Gen Transparent Agent Architecture | GitHub | 2026.03 | | |
| ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents | arXiv | 2026.04 | | |
Applications
Embodied Claws
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks | arXiv | 2026.03 | | |
| RoboClaw (MINT): Open-Source Embodied Intelligence Assistant | GitHub | 2026.03 | | |
| ROSClaw: An OpenClaw ROS 2 Framework for Agentic Robot Control and Interaction | arXiv | 2026.03 | | |
| RoClaw: The Cerebellum — physical embodiment for AI agents | GitHub | 2026.03 | | |
Mobile Claws
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| StreamingClaw Technical Report | arXiv | 2026.03 | | |
| UAV-Claw | GitHub | 2026.04 | | |
Scientific Claws
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| From Agent-Only Social Networks to Autonomous Scientific Research: Lessons from OpenClaw and Moltbook, and the Architecture of ClawdLab and Beach.Science | arXiv | 2026.02 | | |
| Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange | arXiv | 2026.03 | | |
| clawRxiv: Agent-Native Open Research Archive | GitHub / Website | 2026.03 | | |
| AutoResearchClaw:Chat an Idea. Get a Paper. Autonomous, Collaborative & Self-Evolving. | GitHub | 2026.03 | | |
| OpenCLAW-P2P v7.0-P2PCLAW: Resilient Multi-Layer Persistence, Live Reference Verification, and Production-Scale Evaluation of Decentralized AI Peer Review v7.0 -- Mathematical Corrections & Ecosystem Developments Edition | arXiv | 2026.04 | | |
Clinical Claws
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| Autonomous Agent-Orchestrated Digital Twins (AADT): Leveraging the OpenClaw Framework for State Synchronization in Rare Genetic Disorders | arXiv | 2026.03 | | |
| MedOpenClaw: Auditable Medical Imaging Agents Reasoning over Uncurated Full Studies | arXiv | 2026.03 | | |
| OpenClaw-Medical-Skills | GitHub | 2026.03 | | |
| When OpenClaw Meets Hospital: Toward an Agentic Operating System for Dynamic Clinical Workflows | arXiv | 2026.03 | | |
Other Claws
| Title | Venue | Date | Paper | Code |
|---|---|---|---|---|
| DenchClaw | GitHub | 2026.02 | | |
| Scaling Laws for Educational AI Agents | arXiv | 2026.03 | | |
| MathClaw | GitHub | 2026.03 | | |
- Context Kit — Personal Context Artifacts: 4 Markdown templates (wiki, mental-models, voice, protocols) + 5 Claude Code skills. Solves context amnesia — every session starts context-full. MIT, one-command install.
📦 Other Resources
Official Links
| Name | Link |
|---|---|
| OpenClaw Core | github.com/openclaw/openclaw |
| ClawHub Marketplace | clawhub.com |
| Official Docs | docs.openclaw.ai |
SDKs & Tools
| Name | Language | Description |
|---|---|---|
| openclaw-sdk | Python | Build & publish autonomous AI agents |
| mcp-bridge-openclaw | TypeScript | MCP multi-server bridge |
| amor71/openclaw-mcp | TypeScript | Native MCP client |
| henry-y/openclaw-paper-tools | Python | OpenClaw arXiv paper reader |
Automated Research Tools
| Name | Link | Description |
|---|---|---|
| AutoResearchClaw | GitHub | Fully autonomous 23-stage research pipeline: idea → experiment → conference-ready paper; multi-agent peer review |
| OpenClaw-Medical-Skills | GitHub | 869 curated medical AI skills covering clinical work, genomics, drug discovery & bioinformatics |
| ScienceClaw | GitHub | Autonomous research pipeline; 266+ domain skills; 77+ databases |
| ClawCures | GitHub | AI campaign orchestrator for drug discovery; planner/critic loops; ADMET maps |
| clawRxiv | Website | Academic archive for AI agents — 383 agents, 1,827+ papers; affiliated with Stanford–Princeton Claw4S Conference (deadline Apr 30, 2026, prize $50,200) |
| Claw4Science (Claw4S) | Website | First agent-native scientific conference: submit executable skills, not papers; agent peer review; Stanford–Princeton co-organized |
Security References
Benchmarks
| Name | Link | Description |
|---|---|---|
| PinchBench | pinchbench.com · GitHub | 23 real-world tasks across 8 categories; automated + LLM judge grading |
| EvoClaw | evo-claw.com · HuggingFace | Continuous software evolution benchmark; 7 repos / 5 languages / 98 milestones |
Chinese Community & Tutorials
| Name | Link | Description |
|---|---|---|
| OpenClaw China | BytePioneer-AI/openclaw-china | Domestic IM adaption (3,200+ Stars) |
| 中文教程 | openclawgithub.cc | Config & integration guides |
| Hello Claw | Datawhale | Datawhale tutorial |
| 中文站 | clawcn.net | Domestic LLM guide |
| Learn OpenClaw | learnopenclaw.com | Learning platform |
Related Repositories
Know a great OpenClaw project we missed? Open a PR and help us keep this list growing!
| Repository | Stars | Description |
|---|---|---|
| SamurAIGPT/awesome-openclaw | 823 | Comprehensive list of OpenClaw resources, tools, skills, tutorials & articles |
| mergisi/awesome-openclaw-agents | 830+ | 177 production-ready AI agent templates across 24 categories |
| VoltAgent/awesome-openclaw-skills | — | Community curated skills collection |
| community/openclaw-recipes | — | Common automation recipes |
| templates/claw-templates | — | Starter templates for OpenClaw projects |
| pranciskus/discourse-openclaw | NEW | Discourse forum integration with 12 tools |
| wanikua/ByeByeClaw | NEW | One-command uninstaller for all Claw-family agents |
🤝 Contributing
Contributions are welcome! We especially need help with:
- Papers — Adding missing OpenClaw-related papers with proper links.
- Analysis — Improving paper notes, section placement, and taxonomy alignment.
- Timeline — Updating the ecosystem timeline with new events.
- Resources — Adding useful SDKs, tools, benchmarks, datasets, and community repositories.