Open WebUI: self-hosted AI platform, README install and licence notes

What it supplies: The README presents Open WebUI as a self-hosted platform built to run entirely offline, connecting local models through Ollama or OpenAI-compatible APIs. Useful for: - Run a local web interface in front of Ollama or an OpenAI-compatible endpoint. - Deploy with Docker, choosing a standard, slim, CUDA or Ollama-bundled image. - Use the separate desktop app instead of a server install. First action: - Python route: with Python 3.12, run pip install open-webui then open-webui serve, and open port 8080 locally. - Docker route: run the README's docker run command and open port 3000 locally. - Add options such as an Ollama base address or a GPU flag before the image name as needed. Prerequisites and limits: The README states Python 3.12 for the pip route. The CUDA and Ollama image options need the Nvidia Container Toolkit for GPU access. - The licence has a branding requirement, so it should not be assumed to behave like a standard permissive licence. - The slim image depends on external services for embeddings, document extraction and voice. - Configuration and feature details are in the linked documentation, which was not read. Source-documented: the project includes code under the Open WebUI License, which requires preserving the Open WebUI branding, plus earlier contributions under their original licences. Read the linked LICENSE files before rebranding or redistributing. Written from the README text only. Statements are as the README gives them; nothing was installed or run. Based on README text only; the documentation site, licence files and code were not read. No install or run was made. Source inspected: https://raw.githubusercontent.com/open-webui/open-webui/c38885a1a737da4968f157092f304f3b5481d0bf/README.md ; 7126 bytes ; sha256 4441584beee58537e80339450b56617c00b33bf77786576d1599b0d9fe564668 ; 8 exact pinned excerpts in the draft pin map

{
  "revision": {
    "ref": "commit c38885a1a737da4968f157092f304f3b5481d0bf",
    "pinned": false,
    "source_url": "https://raw.githubusercontent.com/open-webui/open-webui/c38885a1a737da4968f157092f304f3b5481d0bf/README.md"
  },
  "checked_at": "2026-11-07T10:39:09.810Z",
  "usefulness": "- Run a local web interface in front of Ollama or an OpenAI-compatible endpoint.\n- Deploy with Docker, choosing a standard, slim, CUDA or Ollama-bundled image.\n- Use the separate desktop app instead of a server install.",
  "source_type": "repository",
  "availability": "available",
  "source_owner": "Open WebUI (declared repository namespace)",
  "known_limitations": [
    "The README states Python 3.12 for the pip route. The CUDA and Ollama image options need the Nvidia Container Toolkit for GPU access.\n\n- The licence has a branding requirement, so it should not be assumed to behave like a standard permissive licence.\n- The slim image depends on external services for embeddings, document extraction and voice.\n- Configuration and feature details are in the linked documentation, which was not read.\n\nSource-documented: the project includes code under the Open WebUI License, which requires preserving the Open WebUI branding, plus earlier contributions under their original licences. Read the linked LICENSE files before rebranding or redistributing.\n\nWritten from the README text only. Statements are as the README gives them; nothing was installed or run.\nBased on README text only; the documentation site, licence files and code were not read. No install or run was made.",
    "Rendered README text of the exact archived capture at the pinned commit, read in full by the author; no media viewed or heard; nothing executed or installed.",
    "Source-documented steps; execution not performed. Internal affiliated review is not independent validation."
  ]
}