Open WebUI

Commands, package names, and image names on this page come from the open-source project that Mibyan Desktop is built on, and can differ from the Mibyan Desktop installer. For the supported Mibyan install and update path, see Install and update.

Open WebUI (126k★) is the most popular self-hosted chat interface for AI. With Mibyan’s built-in API server, you can use Open WebUI as a polished web frontend for your agent — complete with conversation management, user accounts, and a modern chat interface.

Architecture

Open WebUI connects to Mibyan’s API server just like it would connect to OpenAI. Mibyan handles the requests with its full toolset — terminal, file operations, web search, memory, skills — and returns the final response.

Runtime locationThe API server is a Mibyan agent runtime, not a pure LLM proxy. For each request, Mibyan creates a server-side AIAgent on the API-server host. Tool calls run where that API server is running.For example, if a laptop points Open WebUI or another OpenAI-compatible client at a Mibyan API server on a remote machine, pwd, file tools, browser tools, local MCP tools, and other workspace tools run on the remote API-server host, not on the laptop.

Open WebUI talks to Mibyan server-to-server, so you do not need API_SERVER_CORS_ORIGINS for this integration.

Quick Setup

1. Enable the API server

mibyan config set API_SERVER_ENABLED true
mibyan config set API_SERVER_KEY your-secret-key

mibyan config set auto-routes the flag to config.yaml and the secret to ~/.mibyan/.env. If the gateway is already running, restart it so the change takes effect:

mibyan gateway stop && mibyan gateway

2. Start Mibyan gateway

mibyan gateway

You should see:

[API Server] API server listening on http://127.0.0.1:8642

3. Verify the API server is reachable

curl -s http://127.0.0.1:8642/health
# {"status": "ok", ...}

curl -s -H "Authorization: Bearer your-secret-key" http://127.0.0.1:8642/v1/models
# {"object":"list","data":[{"id":"mibyan-agent", ...}]}

If /health fails, the gateway didn’t pick up API_SERVER_ENABLED=true — restart it. If /v1/models returns 401, your Authorization header doesn’t match API_SERVER_KEY.

4. Start Open WebUI

docker run -d -p 3000:8080 \
  -e OPENAI_API_BASE_URL=http://host.docker.internal:8642/v1 \
  -e OPENAI_API_KEY=your-secret-key \
  -e ENABLE_OLLAMA_API=false \
  --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

ENABLE_OLLAMA_API=false suppresses the default Ollama backend, which would otherwise show up empty and clutter the model picker. Omit it if you actually have Ollama running alongside. First launch takes 15–30 seconds: Open WebUI downloads sentence-transformer embedding models (~150MB) the first time it starts. Wait for docker logs open-webui to settle before opening the UI.

5. Open the UI

Go to http://localhost:3000. Create your admin account (the first user becomes admin). You should see your agent in the model dropdown (named after your profile, or mibyan-agent for the default profile). Start chatting!

Docker Compose Setup

For a more permanent setup, create a docker-compose.yml:

services:
  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    ports:
      - "3000:8080"
    volumes:
      - open-webui:/app/backend/data
    environment:
      - OPENAI_API_BASE_URL=http://host.docker.internal:8642/v1
      - OPENAI_API_KEY=your-secret-key
      - ENABLE_OLLAMA_API=false
    extra_hosts:
      - "host.docker.internal:host-gateway"
    restart: always

volumes:
  open-webui:

Then:

docker compose up -d

Configuring via the Admin UI

If you prefer to configure the connection through the UI instead of environment variables:

Log in to Open WebUI at http://localhost:3000
Click your profile avatar → Admin Settings
Go to Connections
Under OpenAI API, click the wrench icon (Manage)
Click + Add New Connection
Enter:
- URL: http://host.docker.internal:8642/v1
- API Key: the exact same value as API_SERVER_KEY in Mibyan
Click the checkmark to verify the connection
Save

Your agent model should now appear in the model dropdown (named after your profile, or mibyan-agent for the default profile).

Environment variables only take effect on Open WebUI’s first launch. After that, connection settings are stored in its internal database. To change them later, use the Admin UI or delete the Docker volume and start fresh.

API Type: Chat Completions vs Responses

Open WebUI supports two API modes when connecting to a backend:

Mode	Format	When to use
Chat Completions (default)	`/v1/chat/completions`	Recommended. Works out of the box.
Responses (experimental)	`/v1/responses`	For server-side conversation state via `previous_response_id`.

Using Chat Completions (recommended)

This is the default and requires no extra configuration. Open WebUI sends standard OpenAI-format requests and Mibyan responds accordingly. Each request includes the full conversation history.

Using Responses API

To use the Responses API mode:

Go to Admin Settings → Connections → OpenAI → Manage
Edit your mibyan-agent connection
Change API Type from “Chat Completions” to “Responses (Experimental)”
Save

With the Responses API, Open WebUI sends requests in the Responses format (input array + instructions), and Mibyan can preserve full tool call history across turns via previous_response_id. When stream: true, Mibyan also streams spec-native function_call and function_call_output items, which enables custom structured tool-call UI in clients that render Responses events.

Open WebUI currently manages conversation history client-side even in Responses mode — it sends the full message history in each request rather than using previous_response_id. The main advantage of Responses mode today is the structured event stream: text deltas, function_call, and function_call_output items arrive as OpenAI Responses SSE events instead of Chat Completions chunks.

How It Works

When you send a message in Open WebUI:

Open WebUI sends a POST /v1/chat/completions request with your message and conversation history
Mibyan creates a server-side AIAgent instance using the API server’s profile, model/provider config, memory, skills, and configured API-server toolsets
The agent processes your request — it may call tools (terminal, file operations, web search, etc.) on the API-server host
As tools execute, inline progress messages stream to the UI so you can see what the agent is doing (e.g. `💻 ls -la`, `🔍 Python 3.12 release`)
The agent’s final text response streams back to Open WebUI
Open WebUI displays the response in its chat interface

Your agent has access to the same tools and capabilities as that API-server Mibyan instance. If the API server is remote, those tools are remote too. If you need tools to run against your local workspace today, run Mibyan locally and point it at a pure LLM provider or pure OpenAI-compatible model proxy (for example vLLM, LiteLLM, Ollama, llama.cpp, OpenAI, OpenRouter, etc.). A future split-runtime mode for “remote brain, local hands” is being tracked in #18715; it is not the behavior of the current API server.

Tool ProgressWith streaming enabled (the default), you’ll see brief inline indicators as tools run — the tool emoji and its key argument. These appear in the response stream before the agent’s final answer, giving you visibility into what’s happening behind the scenes.

Configuration Reference

Mibyan (API server)

Variable	Default	Description
`API_SERVER_ENABLED`	`false`	Enable the API server
`API_SERVER_PORT`	`8642`	HTTP server port
`API_SERVER_HOST`	`127.0.0.1`	Bind address
`API_SERVER_KEY`	(required)	Bearer token for auth. Match `OPENAI_API_KEY`.

Variable	Description
`OPENAI_API_BASE_URL`	Mibyan’s API URL (include `/v1`)
`OPENAI_API_KEY`	Must be non-empty. Match your `API_SERVER_KEY`.

Troubleshooting

Check the URL has /v1 suffix: http://host.docker.internal:8642/v1 (not just :8642)
Verify the gateway is running: curl http://localhost:8642/health should return {"status": "ok"}
Check model listing: curl -H "Authorization: Bearer your-secret-key" http://localhost:8642/v1/models should return a list with mibyan-agent
Docker networking: From inside Docker, localhost means the container, not your host. Use host.docker.internal or --network=host.
Empty Ollama backend shadowing the picker: If you omitted ENABLE_OLLAMA_API=false, Open WebUI shows an empty Ollama section above your Mibyan models. Restart the container with -e ENABLE_OLLAMA_API=false or disable Ollama in Admin Settings → Connections.

Connection test passes but no models load

This is almost always the missing /v1 suffix. Open WebUI’s connection test is a basic connectivity check — it doesn’t verify model listing works.

Response takes a long time

Mibyan may be executing multiple tool calls (reading files, running commands, searching the web) before producing its final response. This is normal for complex queries. The response appears all at once when the agent finishes.

”Invalid API key” errors

Make sure your OPENAI_API_KEY in Open WebUI matches the API_SERVER_KEY in Mibyan.

Open WebUI persists OpenAI-compatible connection settings in its own database after first launch. If you accidentally saved a wrong key in the Admin UI, fixing the environment variables alone is not enough — update or delete the saved connection in Admin Settings → Connections, or reset the Open WebUI data directory / database.

Multi-User Setup with Profiles

To run separate Mibyan instances per user — each with their own config, memory, and skills — use profiles. Each profile runs its own API server on a different port and automatically advertises the profile name as the model in Open WebUI.

1. Create profiles and configure API servers

API_SERVER_* are env vars, not YAML config keys, so write them to each profile’s .env. Pick ports outside the default-platform range (8644 is the webhook adapter, 8645 is wecom-callback, 8646 is msgraph-webhook), e.g. 8650+:

mibyan profile create alice
cat >> ~/.mibyan/profiles/alice/.env <<EOF
API_SERVER_ENABLED=true
API_SERVER_PORT=8650
API_SERVER_KEY=alice-secret
EOF

mibyan profile create bob
cat >> ~/.mibyan/profiles/bob/.env <<EOF
API_SERVER_ENABLED=true
API_SERVER_PORT=8651
API_SERVER_KEY=bob-secret
EOF

2. Start each gateway

mibyan -p alice gateway &
mibyan -p bob gateway &

3. Add connections in Open WebUI

In Admin Settings → Connections → OpenAI API → Manage, add one connection per profile:

Connection	URL	API Key
Alice	`http://host.docker.internal:8650/v1`	`alice-secret`
Bob	`http://host.docker.internal:8651/v1`	`bob-secret`

The model dropdown will show alice and bob as distinct models. You can assign models to Open WebUI users via the admin panel, giving each user their own isolated Mibyan agent.

Custom Model NamesThe model name defaults to the profile name. To override it, set API_SERVER_MODEL_NAME in the profile’s .env:

mibyan -p alice config set API_SERVER_MODEL_NAME "Alice's Agent"

Linux Docker (no Docker Desktop)

On Linux without Docker Desktop, host.docker.internal doesn’t resolve by default. Options:

# Option 1: Add host mapping
docker run --add-host=host.docker.internal:host-gateway ...

# Option 2: Use host networking
docker run --network=host -e OPENAI_API_BASE_URL=http://localhost:8642/v1 ...

# Option 3: Use Docker bridge IP
docker run -e OPENAI_API_BASE_URL=http://172.17.0.1:8642/v1 ...

تطبيق ديسكتوب

البداية

استخدام مبيان

الميزات

منصات المراسلة

التكاملات

الأدلة والدروس

دليل المطوّر

المرجع

Open WebUI

Architecture

Quick Setup

1. Enable the API server

2. Start Mibyan gateway

3. Verify the API server is reachable

4. Start Open WebUI

5. Open the UI

Docker Compose Setup

Configuring via the Admin UI

API Type: Chat Completions vs Responses

Using Chat Completions (recommended)

Using Responses API

How It Works

Configuration Reference

Mibyan (API server)

Open WebUI

Troubleshooting

Connection test passes but no models load

Response takes a long time

”Invalid API key” errors

Multi-User Setup with Profiles

1. Create profiles and configure API servers

2. Start each gateway

3. Add connections in Open WebUI

Linux Docker (no Docker Desktop)

​Architecture

​Quick Setup

​1. Enable the API server

​2. Start Mibyan gateway

​3. Verify the API server is reachable

​4. Start Open WebUI

​5. Open the UI

​Docker Compose Setup

​Configuring via the Admin UI

​API Type: Chat Completions vs Responses

​Using Chat Completions (recommended)

​Using Responses API

​How It Works

​Configuration Reference

​Mibyan (API server)

​Open WebUI

​Troubleshooting

​No models appear in the dropdown

​Connection test passes but no models load

​Response takes a long time

​”Invalid API key” errors

​Multi-User Setup with Profiles

​1. Create profiles and configure API servers

​2. Start each gateway

​3. Add connections in Open WebUI

​Linux Docker (no Docker Desktop)

Architecture

Quick Setup

1. Enable the API server

2. Start Mibyan gateway

3. Verify the API server is reachable

4. Start Open WebUI

5. Open the UI

Docker Compose Setup

Configuring via the Admin UI

API Type: Chat Completions vs Responses

Using Chat Completions (recommended)

Using Responses API

How It Works

Configuration Reference

Mibyan (API server)

Open WebUI

Troubleshooting

No models appear in the dropdown

Connection test passes but no models load

Response takes a long time

”Invalid API key” errors

Multi-User Setup with Profiles

1. Create profiles and configure API servers

2. Start each gateway

3. Add connections in Open WebUI

Linux Docker (no Docker Desktop)