Web LLM Assistant is a lightweight open-source framework that transforms your browser into an AI inference platform. It leverages WebGPU and WebAssembly backends to run LLMs directly on client devices without servers, ensuring privacy and offline capability. Users can import and switch between models such as LLaMA, Vicuna, and Alpaca, chat with the assistant, and see streaming responses. The modular React-based UI supports themes, conversation history, system prompts, and plugin-like extensions for custom behaviors. Developers can customize the interface, integrate external APIs, and fine-tune prompts. Deployment only requires hosting static files; no backend servers are needed. Web LLM Assistant democratizes AI by enabling high-performance local inference in any modern web browser.

FireAct Agent is an open-source React framework designed for building AI-powered conversational agents. It offers a modular architecture that lets you define custom tools, manage session memory, and render chat UIs with rich message types. With TypeScript typings and server-side rendering support, FireAct Agent streamlines the process of connecting LLMs, invoking external APIs or functions, and maintaining conversational context across interactions. You can customize styling, extend core components, and deploy on any web environment.