open-webui
Open WebUI
Decision gist · record as of 2026-08-14
Yes, if you need a self-hosted, feature-complete AI chat platform with RAG and multi-model support. Low install friction, active maintenance, and zero known vulnerabilities are strong signals. However, the custom proprietary license with strict branding restrictions is a material constraint: if you plan to heavily customize or deploy at scale, you will need to negotiate an enterprise license. For private deployments under 50 users or pure self-hosted use, it is a solid choice.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.11 or 3.12; does not support Python 3.13.
- Intended as a server application, not a library.
- Low install friction with a pure Python wheel distribution.
License · maintenance · safety
(unclear) — Licensed under a custom proprietary license with significant branding restrictions: you cannot remove or alter Open WebUI branding except for deployments under 50 end users in a 30-day period, or with explicit written permission or an enterprise license. This limits customized deployments without licensing negotiation.
last release 2026-07-27 (18 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 1,234,828 downloads/mo, #4,178 on PyPI
Alternatives
Verify before relying
pip install open-webui
python -m open_webui.main- Whether the 98 runtime dependencies include optional/conditional installs or are all required for core functionality
- Specific resource requirements (RAM, disk, CPU) for typical deployments
- Whether offline operation requires pre-downloaded models or additional setup beyond pip install
- Default port and access URL for the web interface after startup
What it is and what it does
Open WebUI is a full-featured, self-hosted web application for conversing with language models. It acts as a unified interface to local models via Ollama and remote APIs including OpenAI-compatible endpoints, Azure, and Anthropic, letting you run AI conversations entirely offline or connect to multiple providers. The platform includes built-in retrieval-augmented generation with support for 9 vector databases, web search integration, document upload and parsing, image generation and editing, voice and video calls, and persistent memory across conversations.
It is designed as a server application you deploy and run yourself rather than a library to import. The 98 runtime dependencies reflect its scope: web serving via FastAPI, database support including SQLite and PostgreSQL, cloud storage via boto3 and Azure, authentication via authlib, and AI integrations via anthropic and others. It targets Python 3.11 and 3.12, with a custom proprietary license that restricts branding modifications unless you stay under 50 concurrent users or obtain explicit permission.
Use it for
- Deploy a private AI chat platform for a team without sending data to third-party APIs
- Build a RAG system that ingests documents and lets users query them conversationally
- Create a multi-model evaluation environment comparing responses from different LLMs
- Set up an AI scheduling system with calendar integration and recurring prompt execution
- Integrate multiple AI providers into a single unified chat interface
- Run an offline-first AI assistant with progressive web app support for mobile access
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need a self-hosted, feature-complete AI chat platform with RAG and multi-model support.
Low install friction, active maintenance, and zero known vulnerabilities are strong signals. However, the custom proprietary license with strict branding restrictions is a material constraint: if you plan to heavily customize or deploy at scale, you will need to negotiate an enterprise license. For private deployments under 50 users or pure self-hosted use, it is a solid choice.
Install
open-webui on PyPI
Before you install
Low install friction with a pure Python wheel distribution. Active maintenance with a recent release 18 days old. Requires Python 3.11 or 3.12 (capped below 3.13), and brings in 98 runtime dependencies covering web frameworks, cloud integrations, ML acceleration, and database support.
Requires Python 3.11 or 3.12; does not support Python 3.13. Intended as a server application, not a library.
License in practice
Licensed under a custom proprietary license with significant branding restrictions: you cannot remove or alter Open WebUI branding except for deployments under 50 end users in a 30-day period, or with explicit written permission or an enterprise license. This limits customized deployments without licensing negotiation.
Quickstart
pip install open-webui
python -m open_webui.mainVerify before relying
- Whether the 98 runtime dependencies include optional/conditional installs or are all required for core functionality
- Specific resource requirements (RAM, disk, CPU) for typical deployments
- Whether offline operation requires pre-downloaded models or additional setup beyond pip install
- Default port and access URL for the web interface after startup
Package facts
| License | Not declared unclear |
| Python support | Capped below the current Python release <3.13.0a1,>=3.11 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 98 packagesaccelerateaiocacheaiodnsaiofilesaiohttpaiosqlitealembicanthropicapschedulerargon2-cffiasgirefasync-timeoutauthlibazure-ai-documentintelligenceazure-identityazure-storage-blobbcryptbeautifulsoup4blackboto3brotlibrotlicffichardetchromadbcryptographyddgsdocx2txteinopsfake-useragentfastapi |
| Maintenance | Actively maintained 18 days since the last release |
| First released | |
| Downloads | 1,234,828 / month, #4,178 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaLicense :: Other/Proprietary LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Topic :: Communications :: ChatTopic :: Multimedia |
Evidence: open_webui-0.11.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “self-hosted ai chat interface”
- open-webuiOpen WebUI is a self-hosted AI platform providing a web interface for…
- mindroomMindRoom is a multi-agent runtime that deploys AI agents as…
- litellm-enterpriseLiteLLM Enterprise provides a unified Python SDK and self-hosted AI…
Give your agent the search over MCP, or paste the wish link into any chat.
More Multimedia packages
MoviePy is a Python library for video editing that reads, processes, and writes video and audio files by converting them to numpy arrays for frame-level manipulation and effect application.
Reads metadata (artist, title, duration, bitrate, and more) from audio files in formats including MP3, MP4, FLAC, OGG, WAV, and others, without writing or modifying tags.
Install it if you need to extract metadata from audio files without the overhead of a heavier library.
Converts HTML and CSS to PDF documents using Python, enabling developers with web skills to generate PDF templates without learning specialized PDF libraries.
However, the aging maintenance status (last release 537 days ago) warrants caution in production: verify that its rendering quality and feature set meet your specific…
ffmpy is a Python wrapper around FFmpeg that lets you build and execute FFmpeg command lines programmatically without writing shell commands directly.
Piexif reads, writes, and manipulates EXIF metadata in JPEG and WebP images using pure Python with no compiled dependencies.
Install it if you need to read or edit EXIF in JPEG or WebP files without external dependencies.
Provides PyTorch-native audio data augmentation transforms that run on CPU or GPU, designed to integrate directly into neural network models as differentiable modules.
However, be aware that maintenance is aging (last release 576 days ago), multiprocessing and multi-GPU setups have known limitations, and some transforms have edge…
See also livekit-plugins-openai · litellm-enterprise · abstract-hugpy-dev · open-interpreter · litellm · agent-framework-openai · llama-index-embeddings-azure-openai · bingo-ai · npmai · agent-framework-devui