LIVE
Mistral Makes Large 4 Available as Open Weights29/10/26 · Mistral AI|Gemini 4 Carbon tops the Artificial Analysis Intelligence Index v529/10/26 · Google|Mistral Large 4 now available on Hugging Face29/10/26 · Mistral AI|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|New benchmark checks whether LLMs actually test their temporal medical claims29/10/26|An ODE-based sampling method speeds up discrete diffusion models29/10/26|OpenAI revises its Model Spec with five guiding values for AI behavior29/10/26 · OpenAI|Inside Proton's internal clash over its AI pivot29/10/26 · Proton|Mistral Makes Large 4 Available as Open Weights29/10/26 · Mistral AI|Gemini 4 Carbon tops the Artificial Analysis Intelligence Index v529/10/26 · Google|Mistral Large 4 now available on Hugging Face29/10/26 · Mistral AI|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|New benchmark checks whether LLMs actually test their temporal medical claims29/10/26|An ODE-based sampling method speeds up discrete diffusion models29/10/26|OpenAI revises its Model Spec with five guiding values for AI behavior29/10/26 · OpenAI|Inside Proton's internal clash over its AI pivot29/10/26 · Proton|
AppRisingofficial publisher

Open WebUI

App : A product you use directly

Self-hosted chat interface in the style of ChatGPT, connected to Ollama or any OpenAI API.

The best interface for sharing a local chat with a family or a team.

Official site GitHub · 156,667 ★
Overall score
8.0 /10
Security: one caveat, see the card
Utility
8.5
Reliability
10.0
Security
One caveat
Ease
5 min · Comfortable

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Managing multiple AI models across scattered interfaces, or relying on a cloud service for every conversation, complicates daily use and raises questions about data privacy. Open WebUI addresses this by providing a self-hosted web interface that centralises all your models in one place, without sending your data to a third party.

In practice, you install Open WebUI on your machine or server via Docker or pip, then connect it to Ollama for local models or to any OpenAI-compatible API (LMStudio, GroqCloud, Mistral, OpenRouter, and others). The interface resembles ChatGPT: you create conversations, attach documents, run web searches, and generate images, all from a browser.

Open WebUI suits individuals who want to keep control of their data, families or small teams who want to share an AI assistant on a local network, and organisations that need fine-grained access control, SSO authentication, or air-gapped deployment.

That said, the tool requires some technical knowledge for initial installation and configuration. It is not suited to someone looking for a ready-to-use solution without touching Docker or the command line.

What it offers

  • ·Connection to Ollama and any OpenAI-compatible API (LMStudio, GroqCloud, Mistral, OpenRouter, vLLM, and more) from a single interface.
  • ·Local RAG with support for 9 vector databases, hybrid search, and content extraction from documents or URLs via the # command.
  • ·Integrated web search across many providers (DuckDuckGo, Brave, Bing, Perplexity, Kagi, and others) injected directly into the conversation.
  • ·User management with granular roles, groups, and permissions, plus LDAP, SSO authentication, and SCIM 2.0 provisioning (paid for enterprise features).
  • ·Image generation and editing via DALL·E, Gemini, ComfyUI, or AUTOMATIC1111.
  • ·Hands-free voice and video calls with multiple speech-to-text engines (local Whisper, OpenAI, Deepgram, Azure) and text-to-speech engines.
  • ·Plugin system (Filters, Actions, Pipes, Tools) extensible in Python, with connections to MCP and OpenAPI tool servers.
  • ·Native desktop application for macOS, Windows, and Linux, with a system-wide chat bar and local inference via a built-in llama.cpp engine.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
docker, linux, macos, windows
Licence
Open WebUI License (BSD-3 modifiée)

Security and data

Rating
Security: one caveat, see the card
Your data
Data stays local
Maintenance
Active
Last release
16 October 2026

Links and repository checked on 25 October 2026 · added on 1 October 2023

How to install Open WebUI

1. Make sure Docker is installed on your machine. 2. Run the following command to start Open WebUI (Ollama must be running locally): 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 3. Open your browser at http://localhost:3000. 4. Create the first administrator account on first login: this account has full rights, so choose a strong password. 5. From the admin panel, disable open registration if you do not want others to create accounts freely. 6. If you expose the interface outside your machine, place it behind a reverse proxy with HTTPS.
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

Recipes using Open WebUI

In the same category

Whole category Run locally →