plasmate-labs/plasmate-python
Python SDK for Plasmate - fetch web pages as structured SOM JSON. pip install plasmate.
Wraps the Plasmate CLI to parse web pages into a Semantic Object Model—an LLM-optimized representation that reduces token usage by 10x compared to raw HTML. Built-in parallel fetching via `batch_fetch()` and utility functions for extracting links, text, tables, and headings directly from the SOM. Integrates with LangChain, CrewAI, AutoGen, and Smolagents for AI agent workflows.
Stars
—
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/plasmate-labs/plasmate-python"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
plasmate-labs/plasmate-extension
Chrome extension for exporting auth cookies to Plasmate
plasmate-labs/scrapy-plasmate
Scrapy middleware for Plasmate - replace Splash/Playwright with 10x faster SOM extraction.
plasmate-labs/notebooks
Interactive Jupyter notebooks for Plasmate. Getting started, benchmarks, and integration...
plasmate-labs/plasmate
The browser engine for agents. HTML in, Semantic Object Model out. 5x faster than Lightpanda....
plasmate-labs/autogen-plasmate
Plasmate web browsing tool for Microsoft AutoGen agents. Structured SOM output, not raw HTML.