Starred repositories
Lightpanda: the headless browser designed for AI and automation
Core engine for the Brave browser for mobile and desktop. For issues https://github.com/brave/brave-browser/issues
Lightweight coding agent that runs in your terminal
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
⚛️ Electron bindings for Apple Liquid Glass
On-screen aware AI assistant for your desktop. Uses current app context, multiple LLMs, and MCP tools to help you act across apps.
Capture system loopback audio on macOS 12.3+, Windows and Linux
The headless rich text editor framework for web artisans.
Copy-paste Liquid Glass shader with SVG
Next.js running in Electron: the best way to develop desktop apps
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discr…
A simple CLI tool for interacting with multiple remote Ollama servers, no Ollama installation required
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
MCP server for fetch web page content using Playwright headless browser.
A model context protocol server to work with JetBrains IDEs: IntelliJ, PyCharm, WebStorm, etc. Also, works with Android Studio
A high-performance image compression microservice based on MCP (Modal Context Protocol)
A Model Context Protocol server for Excel file manipulation
Model Context Protocol Servers
🐬DeepChat - A smart assistant that connects powerful AI to your personal world
A lightweight, powerful framework for multi-agent workflows
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs