A benchmark for evaluating LLM × harness performance.

An extremely fast Python type checker and language server, written in Rust.

Write HTML. Render video. Built for agents.

TradingAgents: Multi-Agents LLM Financial Trading Framework

Hyperlight is a lightweight Virtual Machine Manager (VMM) designed to be embedded within applications. It enables safe execution of untrusted code within micro virtual machines with very low latenc…

Benchmarking long-horizon chain-of-thought reasoning.

An open-source AI coding agent that lives in your terminal.

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

Light, fluffy, and always free - The AWS Local Emulator alternative

Dicer auto-sharder: Infrastructure for building sharded services

An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.

The agent that grows with you

Robust Speech Recognition via Large-Scale Weak Supervision

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

JavaScript in-page GUI agent. Control web interfaces with natural language.

Secure, Fast, and Extensible Sandbox runtime for AI agents.

alibaba cloud skills，qwen ，wan and all skills

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Multi-tenant fine-tuning for local LLMs with Tinker-compatible API

A community trust management system based on explicit vouches to participate.

🌈 React for interactive command-line apps

The open source coding agent.

ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Gas Town - multi-agent workspace manager

Open-source, secure environment with real-world tools for enterprise-grade agents.

The official Python SDK for Model Context Protocol servers and clients

A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.

Cutting-edge platform for LLM agent tuning. Deliver RL tuning with flexibility, reliability, speed, multi-agent optimization and realtime community benchmarking.

The batteries-included agent harness.