
open-webui
Self-hosted AI interface for running local and cloud models with extensions and team
- Pricing
- Open source
- Platforms
- Web, macOS, Windows
- GitHub stars
- 159K
- Last commit
- 1 day ago
- Language
- Svelte
- Listing updated
- 2 days ago
Similar tools
About open-webui
open-webui is an open-source AI tool for chatbot. It is available on Web, macOS, Windows, Linux, Self-hosted, API and CLI.
The README says Open WebUI is a self-hosted platform that can run entirely offline, connecting local models through Ollama or any OpenAI-compatible API for both local and cloud models. It installs with pip or uv, runs as a Docker container on port 3000 or 8080, and offers a separate desktop app for macOS, Windows and Linux.
Beyond chat, the project has an ecosystem of companion tools. Open Terminal gives the model a command-line environment for running commands and editing files, Knowledge Base Sync mirrors folders, repos and wikis into knowledge bases, and Open WebUI Computer exposes files, an editor and a terminal in a browser. The website also mentions extending the platform with Python and sharing models, skills and functions through a community library.
It suits individuals and teams who want to keep models and data on their own hardware. The website lists SSO, RBAC, audit logs and air-gapped deployment for regulated organisations, though those enterprise features are described on the vendor's site rather than in the README.
What it does
- Local and cloud models
- Connects to Ollama locally or to OpenAI-compatible APIs for both local and hosted models.
- Docker and pip install
- Runs from a single Docker command or a Python package with a local web address.
- Python extensions
- Lets users extend the interface with Python code, according to the vendor site.
- Community library
- Shares models, skills, tools and functions built by other users.
- Agent terminal support
- Open Terminal gives the model a command environment for running commands and editing files.
- Desktop app
- A native app is available for macOS, Windows and Linux.
Good for
- Run chat models privately on your own machine or server
- Give a team a shared self-hosted interface to several AI models
- Connect an existing Ollama server to a browser-based chat front end
- Mirror internal documents into knowledge bases for model queries
- Let a model run commands and edit files in an isolated environment
Pricing
Open source
Open source under the Open WebUI License, which requires keeping the branding.
Prices change. Check openwebui.com before you buy.
open-webui FAQ
How do I install Open WebUI?
The README gives a pip command (pip install open-webui, then open-webui serve) and a Docker command that serves the interface on port 3000.
Which models can it connect to?
It connects to Ollama and to OpenAI-compatible APIs, covering both local and cloud models.
Where is security reported?
The README says vulnerabilities should be reported privately through GitHub security advisories, and that GitHub is the only accepted channel.
Is open-webui free?
Yes. open-webui is open source, so you can use and self-host it for free.
What are the best alternatives to open-webui?
The closest alternatives to open-webui are Lunabot, BearlyAI, ColossalChat, Android AI Assistant Widget and HotBot.
Where this comes from
- Description: written from the project's README and the project's website.