DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to run a private ChatGPT-style app for your local models with Open WebUI

Start Open WebUI with Docker or pip and chat with Ollama models in the browser.

Short answer: With Docker: docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main; then Or with Python: pip install open-webui, then open-webui serve; open http://localhost:3000 and create the admin account. All steps.

Who it is forSomeone running Ollama who wants a proper chat app instead of the terminal.

The problemLocal models are hard to use day to day without a good interface.

The outcomeA browser chat app at localhost:3000 talking to your local models, offline if you want.

What you need first

  • Docker, or Python with pip
  • Ollama for local models, or an OpenAI-compatible API key
  • A GPU is optional (the :cuda image uses it)

Steps

  1. With Docker: docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
  2. Or with Python: pip install open-webui, then open-webui serve
  3. Open http://localhost:3000 and create the admin account
  4. Pick an Ollama model, or add an OpenAI-compatible API in settings

Prompt for your agent

Install open-webui/open-webui with Docker on this machine, connect it to my local Ollama, and confirm I can chat with <model>. Tell me where chats are stored and how to back them up.

Caveat.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for open-webui/open-webui and "Run a private ChatGPT-style app for your local models"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer