OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Chat & Assistants

Chat UI

Chat UI is an open-source SvelteKit web application for chatting with language models through configurable OpenAI-compatible APIs. It discovers models from the configured service’s `/models` endpoint and provides the interface layer, while the model service remains a separate dependency. The repository describes the codebase as powering HuggingChat.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Chat UI — OpenViST project profile in Chat & Assistants.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Chat UI when you need a web conversation interface and already have, or plan to configure, an OpenAI-compatible model service. Its documented local quickstart suits development; MongoDB options and an optional Docker image provide further deployment paths.

Who it is for

  • Developers building a chat interface around an OpenAI-compatible model endpoint.
  • Teams adapting a self-hosted conversational frontend for their own application.
  • People evaluating a documented SvelteKit and TypeScript codebase for LLM chat.

Documented uses

  • Connect a browser-based chat interface to an OpenAI-compatible API.
  • Run the interface locally during development.
  • Configure MongoDB-backed storage for chat history, users, settings, files and statistics.
  • Customize the app’s displayed name, description and available assets.
  • Configure optional heuristic routing across default, multimodal and agentic routes.
Before you choose

Requirements & limits

The project is a public, open-source GitHub repository. The README documents running the app locally; the model endpoint and any required API key are configured separately.

  • The app supports OpenAI-compatible APIs through OPENAI_BASE_URL; provider-specific integrations and legacy GGUF discovery are described as removed.
  • Model discovery uses the endpoint’s /models route.
  • MongoDB 6/7 can be used for persisted application data; without MONGODB_URL, local development falls back to an embedded database persisting to ./db.
  • An optional Docker image bundles MongoDB, while the README also documents a production build and preview path.
  • The optional heuristic router requires a routes-policy JSON file created by the implementer; no sample file ships with the branch.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Chat UI for local development

Configure an OpenAI-compatible endpoint and start the Chat UI development server locally.

Before you start

  • A local development environment with Git and npm.
  • An OpenAI-compatible API endpoint and its base URL; use an appropriate API key if the endpoint requires one.

Steps

  1. Create a .env.local file with OPENAI_BASE_URL and OPENAI_API_KEY for the endpoint you plan to call.

  2. Clone the huggingface/chat-ui repository and change into its directory.

  3. Run the command below, then the command below.

    Documented command
    npm install
    Documented command
    npm run dev -- --open

  4. Open the local app in a browser and use the configured endpoint to chat.

Expected outcome

The README says the development server runs locally, with the browser opened by the supplied command.

Guide limitations

  • The interface supports OpenAI-compatible APIs only; the configured service must provide the expected protocol and /models endpoint.
  • The repository describes this as a local development setup, not a production deployment.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
huggingface/chat-ui · Official homepage title · retained in its source language
How we review sourcesSuggest a correction