Pricing

Pay per usage

Go to Store

RAG Web Browser

Try for free

Developed by

Apify

Web browser for OpenAI Assistants, RAG pipelines, or AI agents, similar to a web browser in ChatGPT. It queries Google Search, scrapes the top N pages, and returns their content as Markdown for further processing by an LLM. It can also scrape individual URLs. Supports Model Context Protocol (MCP).

4.4 (11)

Pricing

Pay per usage

Total users

2.2k

Monthly users

884

Runs succeeded

>99%

Response time

4.7 days

Last modified

2 hours ago

Open source

Actor uses Standby mode

Beta

The Standby mode is a new, lightweight method for using Actors. Instead of starting an Actor for each input and waiting for results, the Actor remains ready in the background to handle arbitrary HTTP requests, just like any web or API server.

Actor URL

Send a HTTP request to the this URL, and wait for the response. To call the Actor, you need to have an Apify account. Replace <YOUR_API_TOKEN> with your API token, which you can find under Settings > Integrations in Apify Console.Learn more.

To view the specific endpoint of this Actor, go to README.

https://rag-web-browser.apify.actor?token=<YOUR_API_TOKEN>

Max requests per run

maxRequestsPerActorRunnumber

The maximum number of concurrent HTTP requests a single standby Actor run can accept. If this limit is exceeded, the system starts a new Actor run to handle the request, which will take a few seconds.

Default value of this property is 14

Desired requests per run

desiredRequestsPerActorRunnumber

The desired number of concurrent HTTP requests a single standby Actor run can handle. If this limit is exceeded, the system preemptively starts a new Actor run to handle additional requests.

Default value of this property is 10

Memory (MB)

memoryMbytesnumber

The amount of memory (RAM) allocated for the Actor standby run, in megabytes. With more memory, the Actor can typically handle more requests in parallel, but the number of compute units consumed and the cost also grow.

Default value of this property is 8192

Idle timeout (seconds)

idleTimeoutSecsnumber

If a standby Actor run doesn’t receive any HTTP requests in this amount of time, the system will finish the run. When a new request comes, the system might need to start a new standby Actor run to handle it, which will take a few seconds. Higher idle timeout increases the responsiveness but increases the costs as the Actor needs to keep running longer.

Default value of this property is 300

Build

buildenum

Build version of the Actor that will be used for the standby run.

Default value of this property is "version-1"

Actors MCP Server

apify/actors-mcp-server

Connect Apify Actors to AI applications (AI Agents) using Anthropic's Model Context Protocol (MCP). This MCP server provides integration of any Apify Actor through the MCP framework.

Apify

830

Playwright MCP

jiri.spilka/playwright-mcp

A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright

Jiří Spilka

GPT Browser

anchor/gpt-browser

A GPT browser to use OpenAI prompt on any website. Put a list of URLs and a prompt, then the GPT agent will give you the answer you need. Fast, easy, and not limited with OpenAI ChatGPT restrictions. The best way to search and use GPT on large number of websites. Upload Excel or CSV. Screenshots 📸

Anchor

AI Web Agent

apify/ai-web-agent

Use natural language prompts to browse the web, click on elements, fill and submit forms, extract data, and take screenshots using the OpenAI API.

Apify

1.2k

AI Web Scraper - Powered by Crawl4AI

raizen/ai-web-scraper

A blazing-fast AI web scraper powered by Crawl4AI. Perfect for LLMs, AI agents, AI automation, model training, sentiment analysis, and content generation. Supports deep crawling, multiple extraction strategies and flexible output (Markdown/JSON). Seamlessly integrates with Make.com, n8n, and Zapier.

Raizen Technology

Website Content Crawler

apify/website-content-crawler

Crawl websites and extract text content to feed AI models, LLM applications, vector databases, or RAG pipelines. The Actor supports rich formatting using Markdown, cleans the HTML, downloads files, and integrates well with 🦜🔗 LangChain, LlamaIndex, and the wider LLM ecosystem.

Apify

47.5k

Mastra.ai MCP Agent

jakub.kopecky/actor-mastra-mcp-agent

🤖 AI agent using mastra.ai with Apify MCP Server. 🚀 Runs queries via OpenAI models, taps Apify Actors for web data, and outputs to datasets. 🛠️

Jakub Kopecký

Browserbase MCP

jakub.kopecky/browserbase-mcp

A Model Context Protocol (MCP) server that provides browser automation capabilities using Browserbase.

Jakub Kopecký

Web Scraper

apify/web-scraper

Crawls arbitrary websites using a web browser and extracts structured data from web pages using a provided JavaScript function. The Actor supports both recursive crawling and lists of URLs, and automatically manages concurrency for maximum performance.

Apify

81.7k

Dynamic Web Scraper

josejet/dynamic-web-scraper

Dynamic Web Scraper is an Apify Actor that gathers information online by simulating user browsing behavior on the web. It reduces the time and amount of scraped web pages by using a model (ChatGPT) to make decisions regarding browser navigation and results evaluation.