ServiceStack/llms
LLM Client, Server API and UI
What it solves
It provides a lightweight, private alternative to Open WebUI for accessing multiple Large Language Models (LLMs). It focuses on data privacy by keeping all user data stored locally in the browser storage rather than on a remote server.
How it works
The project is a CLI, API, and web interface that allows users to interact with various LLMs. It operates entirely offline (or via local API endpoints) and ensures that conversation history and settings are stored within the browser's own storage mechanisms.
Who it’s for
Users who want a simple, ChatGPT-like interface for their local LLMs without the overhead of a complex UI or the rest of the same data privacy concerns associated with cloud-based AI interfaces.
Highlights
- Lightweight CLI and API
- Browser-based storage for total data privacy
- ChatGPT-like web interface
- Support for multiple LLMs
Related
- Project
Niek/chatgpt-webChatGPT‑web is an open‑source, single‑page web UI that lets you chat with any OpenAI‑compatible LLM (OpenAI, Anthropic, Gemini, etc.). Conversations are stored locally, the app supports voice I/O, image generation, streaming responses, and can be run in the browser, via Docker, or packaged as a native desktop app.
- Project
addyosmani/chattyA private, in-browser AI chat interface that uses WebGPU to run LLMs locally on your hardware for offline use and data privacy.
- Project
chatboxai/chatboxA cross-platform desktop and mobile client for ChatGPT, Claude, and other LLMs that provides a unified interface and local data storage for enhanced privacy.
- Project
amaiya/onpremA privacy-focused Python toolkit for document intelligence that enables local-by-default LLM execution for sensitive data, with optional cloud integration.
- Project
Ryan-yang125/ChatLLM-WebA private, browser-native AI studio and agent workspace that runs LLMs locally on your device using WebGPU, requiring no API keys or backend servers.