Back to directory

Open WebUI

A self-hosted web interface for AI models that works offline with Ollama and OpenAI-compatible APIs, with user roles, plugins, MCP tools, agents, memory and notes.

Open WebUI

Open WebUI is a self-hosted AI platform that gives local and cloud models one interface. It connects to Ollama and to any OpenAI-compatible API, including LM Studio, Mistral, OpenRouter and vLLM.

Administrators set roles, groups and permissions. Plugins add filters, actions, pipes, tools and skills, and external services connect through MCP and OpenAPI tool servers. Models can be wrapped with instructions, tools and knowledge to build agents, and agents can use a terminal and filesystem. It also offers notes, shared channels, persistent memory, calendars, scheduled automations and Markdown and LaTeX support.

It installs with pip, uv, Docker or Kubernetes, and is written in Python.

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.