Sàn agent

🦀️ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/

MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.

🌟 Open Source AI Agent Security Infrastructure — intercepts and blocks dangerous agent behaviors before they happen. Just one command! Join us to build safer Human-AI Symbiosis!

LoongFlow: A Thinking & Learning Framework for Expert-Grade AI Agents.

Multi-Robot Warehouse (RWARE): A multi-agent reinforcement learning environment

Any research. One Claw. 🦞 From any materials to research with fully autonomous & skill-driven researcher.

Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, parallel subagents, persistent sessions, and built-in code review, debugging, security, SEO, accessibility, and compliance tools

[EMNLP 2025] Awesome RAG Reasoning Resources

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

A Graph-Centric Framework for Orchestrating Multi-Agent Systems with Vibe Graphing.

Hands-on workshop: Build a multi-agent AI system from scratch — Deep Research Agent + Writing Workflow served as MCP servers. Includes code, slides, and video

A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.

Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets, and OKX read-only security checks.

An autonomous HR agent that can answer user queries using tools

Durable, Distributed runtime for ALL of your agents - OpenAI, ADK, Langchain, Vercel, etc.

Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.

Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no daemon, no framework.

An open framework to simulate and deploy perception-based PX4/ArduPilot drone swarms with ROS2, YOLO, LiDAR, NVIDIA Jetson

Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.

Plan, Build, and Ship — with a team of AI agents instead of one

本项目为Generative Agents项目的重构+深度汉化版本，旨在为中文用户提供一个利于维护的基础版本，以便后续实验或功能拓展。

AI that ships your tickets.

mahilo: Multi-Agent Human-in-the-Loop Framework is a flexible framework for creating multi-agent systems that can each interact with humans while sharing relevant context internally.

Mac Agent for macOS 26: the agentic AI harness for your Mac Desktop. Computer use, automation, scripting, coding, and more. Powered by 18+ providers across local and cloud LLMs.