Stars
A collection of guides and examples for the Gemma open models from Google.
A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …
MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation Model
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
Specification and documentation for Agent Skills
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"
The all-in-one Vite plugin for React projects.
100+ AI Agent & RAG apps you can actually run — clone, customize, ship.
AI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
The UI design language and React library for Conversational UI
Official JavaScript / TypeScript library for the OpenAI API
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.
A Python-based Xiaozhi AI for users who want the full Xiaozhi experience without owning specialized hardware.
🚀 Powerful Local AI Chat Application - Mcp, Secure, Efficient, Personalized 本地化部署的大模型客户端
Tars is a high-performance RPC framework based on name service and Tars protocol, also integrated administration platform, and implemented hosting-service via flexible schedule.
A lightning-fast, cross-platform AI Assistant App built with React Native.
Integrate the DeepSeek API into popular software
支持 Python3、JavaScript、Shell、Typescript 的定时任务管理平台（Timed task management platform supporting Python3, JavaScript, Shell, Typescript）
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.
DeepEP: an efficient expert-parallel communication library
很多镜像都在国外。比如 gcr 。国内下载很慢，需要加速。致力于提供连接全世界的稳定可靠安全的容器镜像服务。
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.