Open WebUI

Open WebUI is a self-hosted AI platform with a chat interface for local models through Ollama and any OpenAI-compatible API. It installs with pip, Docker or Kubernetes and can run entirely offline.

Open WebUI includes document chat with retrieval across nine vector databases, web search through dozens of providers, image generation, voice and video calls, notes, team channels, persistent memory and a calendar. Admins get roles, groups and permissions, plus dashboards for usage and cost. Plugins, MCP and OpenAPI tool servers extend it further.

Open WebUI is one of the most complete ways to give a person or a team a ChatGPT-style experience on infrastructure you control, with any mix of local and cloud models. Its license adds a branding condition, explained below.

Open WebUI uses its own license: BSD-3-Clause terms plus a branding clause. You can host, modify and use it commercially, but you can't remove or change the Open WebUI name and logo unless your deployment has 50 or fewer users in any 30-day period, or you have written permission or an enterprise license. Because of that clause it isn't open source in the strict sense.

Stars

0

Forks

0

Commits

0

Repository

open-webui/open-webui

• ChatGPTOpenAI's hosted chat app, with conversations stored on OpenAI's servers.
• AnythingLLMNo. 089Open-source AI app for chatting with documents, under the MIT license.
• LobeHubNo. 086Self-hostable AI chat and agent workspace with a modern interface.

See every open-source alternative to ChatGPT in the collection.