Open-source Apify alternatives

Skyvern automates browser-based workflows using large language models and computer vision. It offers a Playwright-compatible SDK that adds AI capabilities on top of Playwright, and a no-code workflow builder so that both technical and non-technical users can automate manual tasks on any website, replacing brittle automation scripts.

Traditional browser automation depends on custom scripts for each site, often relying on DOM parsing and XPath selectors that break whenever the layout changes. Skyvern instead relies on vision-capable LLMs to understand and interact with pages. Its design was inspired by task-driven autonomous agents such as BabyAGI and AutoGPT, with the added ability to act on sites using browser automation libraries. A swarm of agents comprehends a website, plans actions and executes them.

Skyvern is written in Python and licensed under AGPL-3.0, and topics note RPA and workflow use. You can self-host it or use the hosted service at skyvern.com. It targets teams that automate tasks across many different websites, such as form filling or data retrieval, where writing and maintaining per-site scripts is costly.

Maxun is an open-source platform for getting structured data out of websites. Its pitch is to turn any site into an API: you can scrape pages, crawl links, search, monitor for changes and use AI-powered extraction, without having to hand-code a scraper for every site. Topics tag it as a no-code, RPA and browser-automation tool.

It is built on Playwright-style browser automation, written in TypeScript, and is meant to be used through a visual interface so that people who do not code can create data-extraction robots. The project offers a hosted app and documentation, tutorials and a Discord community, and it can be self-hosted. The README is heavily sponsored by proxy providers, which reflects how scraping at scale usually needs rotating proxies, though those are third-party services that are not part of Maxun itself.

Maxun is licensed under AGPL-3.0, which requires sharing source changes if you offer a modified version as a network service. It suits analysts, marketers and developers who regularly pull data from websites without official APIs, and who want a managed or self-run alternative to custom scraping scripts.

AnakinScraper OSS is an open-source web scraping API aimed at AI use cases. It converts web pages into markdown ready for language models or into structured data, and it can be self-hosted with a single command with no cloud dependencies. It is written in Go and released under the AGPL-3.0 license.

The README highlights an anti-detect browser based on Camoufox, a Firefox build, smart proxy selection using Thompson Sampling, a handler chain that falls back from plain HTTP to a browser and then an API, and structured JSON extraction using Gemini. It can start with go run without a database and ships as one small Go binary, in contrast to the Node.js or Python based tools it compares itself against, including Firecrawl, Crawlee, and Scrapy.

It is meant to power RAG pipelines, AI agents, and data extraction at scale. Anyone scraping should check the target site's terms and applicable law. It suits developers who want a private, self-run alternative to hosted scraping APIs.