Jurl
curl that reads the page for you
About Jurl
Tell it what you want. It picks it out of the page. Fast, cheap, open source.
In the maker’s words
jurl is a CLI. Tell it what you want from a page and it picks exactly that out: the paragraphs that answer a question, the code, the links worth following, or a photo you describe. On Wikipedia's Cologne page it finds the cathedral among 73 images in 2.3 s; on the Jevons page, the two paragraphs out of ~240 that explain his paradox. The link above lets you try it in the browser, no key needed. Or in your terminal, with your own TypeSafe key (it asks for it on first run): brew install rayoplateado/tap/jurl jurl -q "What is the Jevons paradox?" en.wikipedia.org/wiki/William_Stanley_Jevons jurl --code github.com/BurntSushi/ripgrep jurl -f "a cathedral" en.wikipedia.org/wiki/Cologne jurl -l -n 3 news.ycombinator.com | xargs -n1 jurl -n 1 How it works: jurl splits the page into blocks, links and images, and turns each one into a yes/no question ("does this block answer the question?"). A deci…
Where people found it
- Hacker NewsShow HN: Jurl – curl that reads the page for you6 points2 comments4 hours ago
More sites like Jurl
- Giving Opus 5.5 a simulated paint canvasstillwet.art
- photocraftAn open-source, clean-room reimplementation of Adobe Photoshop in pure Rust
- OpenDotsYour always-on AI coworkers that move between text, calls, and Slack.
- EraComplete Simulated Companies for Your Agents
- Ledge.shRunnable Markdown Notes
- Pi podRun your pi coding agent in sandboxes on your own server