Sàn agent

A collection of multi agent environments based on OpenAI gym.

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.

A codex plugin for running optimization loops inside a codebase. It is useful when you have a measurable target and many possible changes to try: test runtime, build speed, bundle size, model loss, Lighthouse scores, memory use, query latency, or any other metric you can print from a script.

Govern, Observe, Direct - a real-time control room for agent societies

If you can read ~100 lines of Python, you understand agents.

The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.

Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

Fusing GPS, IMU and Encoder sensors for accurate state estimation.

An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.

Pack and deploy local AI agents for your team in minutes

Shell and coding agent on mcp clients

RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.

Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.

A multi-agent framework written in Rust that enables you to build, deploy, and coordinate multiple intelligent agents

AI Scraper is a powerful scraping tool and scrape agent built to automate data extraction with unmatched precision. Ideal for scalable AI scraping tasks across diverse web sources, this tool simplifies complex scraping operations into efficient, intelligent workflows.

Version-Control for AI coding agents.

The only browser automation that bypasses anti-bot systems. AI writes network hooks, clones UIs pixel-perfect via simple chat.

Give Claude/Cursor email powers. 27 MCP tools — inbox, send, reply, contacts, search. Free, no signup.

飞书插件 × OpenClaw 保姆级配置指南 & 社区支持 （0328 - 更新飞书cli调用指南，增加 API 耗尽根因排查、Lark Webhook 内网穿透方案）

OpenBiliClaw 是纯本地、私有、开源的自进化跨平台内容发现 Agent：从跨平台使用、项目反馈与对话中持续深化心理画像，带着对你的理解主动去 B 站、小红书、抖音、YouTube 等来源找内容 / Fully local, private, open-source, self-improving discovery agent that learns from usage, feedback, and dialogue to find content across Bilibili, Xiaohongshu, Douyin, YouTube, and more.

Autonomous Android and computer use using any LLM (local or remote)

Open-source local-first AI agent for desktop work. No account, no telemetry: use local models with Ollama/Rapid-MLX or bring your own provider key.

Track token usage across 22 AI coding tools (Claude Code, Codex, Cursor, Gemini, Roo Code, Zed Agent, Goose, and more) — local-first, zero-config, with a beautiful dashboard, native macOS menu bar app, and 4 desktop widgets.

🐝 Multi-agent swarm coordination for OpenCode with learning capabilities, agent issue tracking, and management