whereismyai
HuggingChat UI
HuggingChat UI is an open source chat interface for large language models that connects to OpenAI-compatible APIs.
Chat UI is a SvelteKit application that serves as a chat interface for large language models. It connects to OpenAI-compatible APIs such as the Hugging Face Inference Providers router, llama.cpp server, Ollama, OpenRouter, and Poe. It stores chat history, users, settings, files, and stats in MongoDB, supporting both managed MongoDB Atlas and local containers or embedded instances. The application includes optional features like server-side smart routing, Model Context Protocol tools integration, and an experimental ML Intern mode for machine learning tasks. It is designed for developers and teams looking to host their own customizable chat application.
HuggingChat UI at a glance
- Best for: Software engineer
- Runs on: Web, Docker, self-hosted, open source
- Pricing: Free
- Released: February 2023
- Category: AI chat assistant
- Website: github.com/huggingface/chat-ui
Key features
- Connect to OpenAI-compatible APIs
- Store chat data in MongoDB
- Configure server-side smart routing
- Run Model Context Protocol tools
- Customize themes and app branding
- Use experimental ML Intern mode
Use it for
- Chatting with large language models locally or via APIs
- Hosting a private chat application for teams
- Running machine learning tasks with ML Intern
- Integrating tool calls via Model Context Protocol servers
Companions
Tools that articles about HuggingChat UI recommend using with it, each with its job.
- Ollama — Run open models locally or in the cloud with private prompts
- SearXNG — Built-in integration for web-grounded answers.
- ComfyUI — Local image and video generation on a node canvas, with every model and parameter in reach
- LiteLLM — Per-user keys and routing for clients outside the web UI.
- Hermes Agent — Adds agentic workflows on the same local models.
- Cloudflare Tunnel — Reach the homelab without opening ports.
Alternatives to HuggingChat UI
- LibreChat — Unifies multiple AI models and tools in one customizable, open-source platform.
- Hugging Face — Home of open-source AI models and the Transformers library
- Open WebUI — Run AI on your own terms with complete data privacy and self-hosting control.
- huggingface.js — Connects JavaScript applications directly to Hugging Face models and services.
- llmspy.org — Self-host access to 530+ AI models across 24 providers with built-in tools.
- 5ire — It supports local knowledge base management and Model Context Protocol servers.
- RikkaHub — Integrates a Linux workspace for AI agents on Android devices.
- Uniichat — Maintains one unending chat with a memory tree that never loses historical detail.
- Maid — Run models locally on-device or connect to remote providers securely.
- Text Generation WebUI — Run local LLMs with multiple backends, multimodal input, and tool calling 100% offline.
- Chuanhu Chat — Provides a clean user interface with multi-model support and local deployment.
- Enchanted — Private, unfiltered, and multimodal chat across the Apple ecosystem.
All HuggingChat UI alternatives