Starred repositories
🦜🔗 Build context-aware reasoning applications
Build resilient language agents as graphs.
open source interpretability platform 🧠
AgentScope: Agent-Oriented Programming for Building LLM Applications
Dark mode by default. An unofficial fork of https://github.com/Kaidesuyo/Hydrogen-Music
仿明日方舟工业风音乐播放器，支持添加曲绘
PyTorch code and models for VJEPA2 self-supervised learning from video.
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
MCP Toolbox for Databases is an open source MCP server for databases.
A GUI client for Windows, Linux and macOS, support Xray and sing-box and others
No fortress, purely open ground. OpenManus is Coming.
AgentNetworkProtocol(ANP) is an open source protocol for agent communication. Our vision is to define how agents connect with each other, building an open, secure, and efficient collaboration netwo…
[! important] Repository has been moved to a new address【仓库已迁移☞】: https://github.com/agent-network-protocol/AgentNetworkProtocol
A model context protocol server to work with JetBrains IDEs: IntelliJ, PyCharm, WebStorm, etc. Also, works with Android Studio
A high-throughput and memory-efficient inference and serving engine for LLMs
Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization
An open protocol enabling communication and interoperability between opaque agentic applications.
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
The official Python SDK for Model Context Protocol servers and clients
Model Context Protocol Servers
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.
This is the official repository for The Hundred-Page Language Models Book by Andriy Burkov
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling