web-llm

Private local model studio, AI chat, and agent workspace powered by WebGPU and WebLLM.

🚀 Zero-backend, 100% client-side local AI assistant starter template. Powered by WebGPU and Google LiteRT-LM (Gemma 4). Offline-first PWA with multi-language TTS, customizable personas, and GitHub Pages deployment in 5 minutes.

◉ Universal Intelligence: AI made simple.

WebLLM Gateway：让 Qwen/DeepSeek 网页模型接入 OpenAI/Anthropic 兼容 Agent 工具链，支持 OpenClaw、Hermes、Claude Code、Codex 工具调用

Interactive 3D Git history visualizer & time-travel explorer with AI-powered codebase lore

LocalPlexity is a lite version of Perplexity aimed at 100% privacy and openness. Everything is done locally, in your browser, from searching the web to distilling a response for your question.

Rocus is an intelligent, AI-powered knowledge graph that automatically organizes your saved websites using local machine learning models. Built with Vue.js, D3.js, and WebGPU-accelerated AI, Rocus runs entirely in your browser with no servers, no cloud, complete privacy.

WhyAI – Inteligencia artificial generativa híbrida (offline y online) en navegador, privada.

A privacy-first AI writing assistant running entirely in your browser using WebGPU and Llama-3. No server, no data leakage.

👀 tracksy - Visualize your data

A completely front-end driven AI agent project, requiring no server resources.

Worker pool for running AI models in the browser — WebGPU/WASM auto-detection, streaming, cross-tab dedup

Use the online Gemini, Open AI or its compatible (v1/chat). Use offline with: @mlc-ai/web-llm, transformers.js-Whisper onnx, esearch-ocr. supports PWA to achieve offline conversation translation without restrictions.

Run 100+ open-source LLMs entirely in your browser. No servers, no API keys, 100% private. Powered by WebGPU and WebLLM.

A low-poly ecosystem simulator featuring real-time dynamic terrain, GPU-accelerated water flow, resource management, and local LLM integration for AI entity behavior. Built with React, Three.js, and Web-LLM.

End-to-end structured output for browser LLMs. Constrain Transformers.js/web-llm to valid JSON/SQL via GBNF grammars.

A React UI for Web LLM 💬

Build and export local AI workflows as a single HTML file. Runs 100% in your browser via WebGPU. No server, no API keys, no data leaks.

View and chat to your K8s cluster & application logs. K9s themed dashboard, REST API+MCP server. In browser chat using OpenAI API or local WebLLM. Brew installable.