Web Scraping Agents
Tools and SDKs for extracting structured data from web pages optimized for AI agents. Includes framework integrations, language-specific clients, and performance benchmarks. Does NOT include general web scraping libraries, crawlers without agent optimization, or non-web data extraction tools.
There are 17 web scraping agents tracked. The highest-rated is plasmate-labs/plasmate-a11y at 22/100 with 0 stars.
Get all 17 projects as JSON
curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=agents&subcategory=web-scraping-agents&limit=20"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
| # | Agent | Score | Tier |
|---|---|---|---|
| 1 |
plasmate-labs/plasmate-a11y
Accessibility auditing via Plasmate's Semantic Object Model. 7 WCAG rules,... |
|
Experimental |
| 2 |
plasmate-labs/plasmate
The browser engine for agents. HTML in, Semantic Object Model out. 5x faster... |
|
Experimental |
| 3 |
plasmate-labs/autogen-plasmate
Plasmate web browsing tool for Microsoft AutoGen agents. Structured SOM... |
|
Experimental |
| 4 |
plasmate-labs/plasmate-audit
Site auditing powered by Plasmate. 10x faster than Chrome-based auditors.... |
|
Experimental |
| 5 |
plasmate-labs/crewai-plasmate
Plasmate web browsing tool for CrewAI agents. 10x fewer tokens than raw HTML... |
|
Experimental |
| 6 |
plasmate-labs/smolagents-plasmate
Plasmate web browsing tool for HuggingFace Smolagents. Give your agent... |
|
Experimental |
| 7 |
plasmate-labs/plasmate-benchmarks
Reproducible benchmarks for Plasmate. Token compression, latency, and... |
|
Experimental |
| 8 |
plasmate-labs/notebooks
Interactive Jupyter notebooks for Plasmate. Getting started, benchmarks, and... |
|
Experimental |
| 9 |
plasmate-labs/plasmate-extension
Chrome extension for exporting auth cookies to Plasmate |
|
Experimental |
| 10 |
plasmate-labs/plasmate-python
Python SDK for Plasmate - fetch web pages as structured SOM JSON. pip... |
|
Experimental |
| 11 |
plasmate-labs/scrapy-plasmate
Scrapy middleware for Plasmate - replace Splash/Playwright with 10x faster... |
|
Experimental |
| 12 |
plasmate-labs/som-action
GitHub Action: fetch a web page with Plasmate and output SOM JSON. Use in CI... |
|
Experimental |
| 13 |
plasmate-labs/awesome-plasmate
A curated list of tools, integrations, and resources for Plasmate - the... |
|
Experimental |
| 14 |
plasmate-labs/quickstart-rust
Quickstart template: use Plasmate with Rust. Fetch any URL and get... |
|
Experimental |
| 15 |
plasmate-labs/quickstart-node
Quickstart template: use Plasmate with Node.js. Fetch any URL and get... |
|
Experimental |
| 16 |
plasmate-labs/replit-template
Try Plasmate in your browser. Replit template for the browser engine for AI agents. |
|
Experimental |
| 17 |
plasmate-labs/quickstart-python
Quickstart template: use Plasmate with Python. Fetch any URL and get... |
|
Experimental |