Back to directory

nextjs-vllm-ui

A self-hosted, ChatGPT-style web interface for vLLM and Ollama, built with Next.js, that runs entirely in the browser with chats stored in local storage.

nextjs-vllm-ui

nextjs-vllm-ui is a web interface for chatting with a locally or self-hosted vLLM or Ollama server, forked from an existing Ollama-focused UI project. It stores chat history in the browser's local storage rather than a database, works on both desktop and mobile, highlights code blocks with one-click copying, and supports light and dark themes.

It is distributed as a Docker image, run by pointing an environment variable at a running vLLM, or, with two further variables set, an Ollama, server, including over a Docker host network when the model server runs on a different address. For local development it can also be cloned and run directly with Node.js 18 or newer.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.