Stars
DeepSeek Harness: Everything is a Plugin.
The agent that grows with you
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Model Context Protocol Servers
The first open-source, cross-platform library for text selection monitoring and global mouse/keyboard event hooks — production-grade, for Node.js and Electron.
Fast, customizable Markdown parser and renderer with full CommonMark support. TypeScript rewrite of markdown-it with enhancements.
Tiny and powerful JavaScript full-text search engine for browser and Node
SGLang is a high-performance serving framework for large language models and multimodal models.
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
A high-throughput and memory-efficient inference and serving engine for LLMs
基于MCP(Model Context Protocol)的智能聊天应用，支持Web和桌面环境。集成OpenAI/Anthropic API，提供MCP服务器的所有工具能力。简洁现代的UI设计，支持跨平台部署。
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
A highly customizable Flowchart component for Vue 3. Features seamless zoom & pan 🔎, additional components like a Minimap 🗺 and utilities to interact with state and graph.
Build cross-platform desktop apps with JavaScript, HTML, and CSS
Pre-builds Tree-Sitter WASM files
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Retrieval and Retrieval-augmented LLMs
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
OpenAI Whisper ASR Webservice API
Faster Whisper transcription with CTranslate2