VictoriaMetrics: fast, cost-effective monitoring solution and time series database

Understanding neural networks with dictionary learning

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

LlamaIndex is the leading framework for building LLM-powered agents over your data.

🦊 Anti-detect browser

Tools for merging pretrained large language models.

[ICML'24 Spotlight] "TravelPlanner: A Benchmark for Real-World Planning with Language Agents"

OctoTools: An agentic framework with extensible tools for complex reasoning

The open-source AI-native IDE

A CLI host application that enables Large Language Models (LLMs) to interact with external tools through the Model Context Protocol (MCP).

A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.

Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

The official Python SDK for Model Context Protocol servers and clients

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

A cross-platform GUI automation Python module for human beings. Used to programmatically control the mouse & keyboard.

A tiny but valid `init` for containers

All of the ad-hoc things you're doing to manage incidents today, done for you, and much more!

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

A simple screen parsing tool towards pure vision based GUI agent

🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.

DeepEP: an efficient expert-parallel communication library

FlashMLA: Efficient Multi-head Latent Attention Kernels

UPX - the Ultimate Packer for eXecutables

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

A high-throughput and memory-efficient inference and serving engine for LLMs

MLX: An array framework for Apple silicon

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.