An in-the-wild benchmark for AI agents in the OpenClaw Environment.

The official repository of ATIR: Towards Audio-Text Interleaved Contextual Retrieval

This is the official repository of R^3AG. We propose R³AG, a retriever-aware routing framework for retrieval-augmented generation that models query-specific preferences by jointly learning retrieva…

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai

Toolathlon-Gym for testing AI agents real-world tool-use capabilities across diverse MCP servers.

OpenClaw 中文官方技能库 | 翻译自 Clawdbot 官方技能，按场景分类整理，支持中文自然语言调用

🇨🇳 OpenClaw中文用例大全 | 49个真实场景 | 国内特色 + 海外案例的国内适配 | 自动化办公·内容创作·运维·AI助理·知识管理 | 新手友好 | Chinese guide for OpenClaw AI agent use cases

"ClawTeam: Agent Swarm Intelligence" (One Command → Full Automation)

[ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

A list of awesome papers and resources of agent harness engineering.

OpenClaw-RL: Train any agent simply by talking

slime is an LLM post-training framework for RL Scaling.

Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

Automated paper discovery skill — daily HF Papers digest + one-click deep reading via SwiftScholar, powered by OpenClaw.

Claw-R1: Empowering OpenClaw with Advanced Agentic RL.

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…

RepoLaunch is an agentic SWE tool aimed at automating the build, execution and test of GitHub repositories across programming languages and operating systems.

A community collection of OpenClaw use cases for making life easier.

Harbor is a framework for running agent evaluations and creating and using RL environments.

"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"