io.github.manuelinuxkr/substrate-browserweb-automation

substrate-browser

Verified · today

Token-first headless browser for AIs. Extracts a tiny semantic graph, cutting HTML bloat by 95%.

Install

claude mcp add substrate-browser -- npx -y [email protected]

Requires: SUBSTRATE_PROXY, SUBSTRATE_VIEWPORT_WIDTH, SUBSTRATE_VIEWPORT_HEIGHT

Our take

This is a headless browser server optimized for AI usage, with an emphasis on extracting a compact semantic representation instead of returning full HTML. It is for agent builders who want browser automation with lower token overhead than conventional page dumps. The concept is interesting, but the zero-star footprint suggests an early-stage project that deserves hands-on validation before relying on it in production.

reviewed by hand · 2026-09-02

Something wrong or dead here? Report it

Verification record

last verified
today
github stars
0
last commit
today
archived
no
license
MIT
npm
substrate-browser
latest version
2.0.2
in registry since
2026-09-01

github.com/manuelinuxkr/substrate-b

More in web-automation

browse all →
browser-useweb-automation

browser-use

Verified · yesterday

Control a real Chrome browser to complete any task: fill forms, extract data, book flights.

hand-reviewed112k starschecked yesterday

Scraplingweb-automation

Scrapling MCP Server

Verified · 21 days ago

Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.

hand-reviewed74k starschecked 21 days ago

skyvernweb-automation

Skyvern

Verified · 20 days ago

AI-powered browser automation — navigate, click, fill forms, and extract data from any website.

hand-reviewed23k starschecked 20 days ago

apify-mcp-serverweb-automation

apify-mcp-server

Verified · 24 days ago

Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡

hand-reviewed3.0k starschecked 24 days ago