# Crawl4AI Proxy

Crawl4AI Proxy is a self-hosted tools & utilities app. A lightweight proxy that bridges Open WebUI's external web loader to Crawl4AI. It is open source and self-hosted, installable on Docker Hub and Unraid.

Canonical page: https://ourlocalhost.com/app/2387/crawl4ai-proxy

## Description

A lightweight proxy that bridges Open WebUI's external web loader to Crawl4AI. It uses Crawl4AI's headless browser to fetch clean markdown from JavaScript-heavy or bot-protected pages, giving AI chat sessions more reliable, higher-quality web-search results for self-hosters running Open WebUI.

## Platform availability

Available on 1 of 9 platforms: Unraid.

## Health score

42/100 (Fair), based on 3 of 4 factors.
- Maintained: 75 (last commit 25 days ago)
- Popular: 6 (1 GitHub stars)
- Easy to install: 20 (1 install platform, Docker image)

## Links

- Docker Hub: https://hub.docker.com/r/zkkzkk32312/crawl4ai-proxy
- GitHub: https://github.com/zkkzkk32312/crawl4ai-proxy
- Unraid: https://ca.unraid.net/apps/crawl4aiproxy-1g2dqp107yo7dl?q=Crawl4AIProxy

## Common questions

### Why would I add this proxy instead of using Open WebUI's built-in web loader?

Open WebUI's default web loader can struggle with JavaScript-heavy pages and bot detection. This proxy uses Crawl4AI's headless browser to fetch clean markdown content from URLs.

### What authentication and network defaults does the self-hosted Crawl4AI Docker server use?

It requires authentication by default and binds to loopback unless you set a token. It also validates request bodies against a strict trust boundary.

### Can this avoid using a paid web-search API service?

It can be run in Docker to connect Open WebUI with Crawl4AI and make web search usable without paying for an API service.

---
Source: Our Local Host (https://ourlocalhost.com/app/2387/crawl4ai-proxy), the self-hosted and open-source app directory.