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

How to share one AI workspace with your team, with roles and groups with Open WebUI

Run Open WebUI on a server and give each person the models and tools their role needs.

Short answer: Deploy with Docker or Kubernetes on a team server; then use PostgreSQL instead of SQLite for a larger team; create user groups and roles with granular RBAC. All steps.

Credentials. Admin access controls every user's chats and connected API keys; protect the admin account.

Who it is forA small company that wants one internal AI chat with access control.

The problemEveryone using their own personal AI accounts means no control and duplicated cost.

The outcomeOne shared instance with user groups, per-group model access and custom agents.

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. Deploy with Docker or Kubernetes on a team server
  2. Use PostgreSQL instead of SQLite for a larger team
  3. Create user groups and roles with granular RBAC
  4. Build custom models and agents with instructions, tools and knowledge, and limit them per group

Prompt for your agent

Plan an open-webui/open-webui deployment for <n> people on <server>: storage choice, groups and roles for <teams>, and which models each group gets. Then give me the Docker command.

Caveat.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for open-webui/open-webui and "Share one AI workspace with your team, with roles and groups"

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