What do you want to do?
3 use cases
-
Convert web pages to markdown for an LLM
Use lightpanda fetch to render a page, run its JavaScript, and dump clean markdown or structured data while obeying robots.txt.
View prompt
Using lightpanda-io/browser, run lightpanda fetch with --obey-robots and --dump markdown on each URL in <my list> and save one markdown file per page.
-
Run existing Puppeteer scripts on a lighter Browser
Start the Lightpanda CDP server and point puppeteer.connect at it, keeping the rest of your script the same.
View prompt
With lightpanda-io/browser, start the CDP server on 127.0.0.1:9222 and change <my Puppeteer script> to connect with browserWSEndpoint, then compare its run time against Chrome.
-
Give an AI agent a Browser through MCP or agent mode
Add Lightpanda as an MCP server for your coding agent, or use lightpanda agent to describe a task in plain English and save it as a replayable script.
View prompt
Using lightpanda-io/browser, add the lightpanda MCP server to my agent config, then use it to open <a page> and extract its title and links.
Quick start with Browser
- Check you have what it needs: Linux or macOS (x86_64 or aarch64); Windows only through WSL2; Linux binaries need glibc; Install with `brew install lightpanda-io/browser/lightpanda`, a nightly binary, Nix or `docker run -d --name lightpanda -p 127.0.0.1:9222:9222 lightpanda/browser:latest`; puppeteer-core or Playwright if you connect your own scripts over CDP.
- Open lightpanda-io/browser on GitHub and read the README and license.
- Install with
brew install lightpanda-io/browser/lightpanda, or download the nightly binary and check it with./lightpanda version - Dump a page with
./lightpanda fetch --obey-robots --dump html --log-format pretty --log-level info https://demo-browser.lightpanda.io/campfire-commerce/ - Swap in
--dump markdownfor markdown, or--dump structured_datafor JSON-LD, OpenGraph and meta tags - Use
--wait-selectoror--wait-mswhen content loads late
These steps come from our top use case, Convert web pages to markdown for an LLM, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for lightpanda-io/browser
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forDevelopers running scrapers, crawlers or agent browsing at scale who want lower memory and faster pages than Chrome.
- Why it is hot39k stars, talked about in 2 AI sources we track
- Sourcegithub.com/lightpanda-io/browser ยท Back to Hot repos
Requirements
- Linux or macOS (x86_64 or aarch64); Windows only through WSL2; Linux binaries need glibc
- Install with `brew install lightpanda-io/browser/lightpanda`, a nightly binary, Nix or `docker run -d --name lightpanda -p 127.0.0.1:9222:9222 lightpanda/browser:latest`
- puppeteer-core or Playwright if you connect your own scripts over CDP
Add this badge to your README
Maintain Browser? Show readers where to find these use cases.
Markdown
[](https://dedupedai.com/use-cases/lightpanda-io-browser/?utm_source=github&utm_medium=badge&utm_campaign=lightpanda-io-browser)
HTML
<a href="https://dedupedai.com/use-cases/lightpanda-io-browser/?utm_source=github&utm_medium=badge&utm_campaign=lightpanda-io-browser"><img src="https://dedupedai.com/badge/lightpanda-io/browser.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Browser
What is Browser?
Lightpanda is a headless browser written from scratch in Zig for AI agents and automation, not a Chromium fork. It can dump pages as HTML, markdown, PNG, PDF or structured data, serves CDP and WebDriver BiDi so Puppeteer and Playwright scripts can connect, and has a native agent mode and MCP server. The README benchmark shows about 16x less memory and 9x faster than headless Chrome on 100 pages. It is an open-source project on GitHub: https://github.com/lightpanda-io/browser.
How do I use Browser?
Install with brew install lightpanda-io/browser/lightpanda, or download the nightly binary and check it with ./lightpanda version; then Dump a page with ./lightpanda fetch --obey-robots --dump html --log-format pretty --log-level info https://demo-browser.lightpanda.io/campfire-commerce/; Swap in --dump markdown for markdown, or --dump structured_data for JSON-LD, OpenGraph and meta tags. The use cases on this page give the full steps and a copy-paste agent prompt for each job.
Who is Browser for?
Developers running scrapers, crawlers or agent browsing at scale who want lower memory and faster pages than Chrome.
What can I do with Browser?
3 use cases so far, for example: Convert web pages to markdown for an LLM; Run existing Puppeteer scripts on a lighter Browser; Give an AI agent a Browser through MCP or agent mode. Each has steps and a copy-paste agent prompt.
What do I need to run Browser?
Linux or macOS (x86_64 or aarch64); Windows only through WSL2; Linux binaries need glibc; Install with `brew install lightpanda-io/browser/lightpanda`, a nightly binary, Nix or `docker run -d --name lightpanda -p 127.0.0.1:9222:9222 lightpanda/browser:latest`; puppeteer-core or Playwright if you connect your own scripts over CDP.
What are alternatives to Browser?
Other hot AI repos in Software and DevOps: Skills, Claude Mem, Freellmapi, Andrej Karpathy Skills, Agent Desktop.
Is Browser safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.