Browser extension to create reliable CSS and XPath selectors using AI. You can use it to create a selector for a single element or for an array of elements. The selectors it creates are meant to be "semantic" and more resilient to page changes! Extension is also open source on GitHub: https://github.com/Intuned/selector-forge
Hey everyone! I'm Ahmad, co-founder at Intuned. Excited to share Selector Forge.
Selector Forge is a free browser extension that uses AI to generate reliable CSS and XPath selectors. You can create one for a single element or for a list of elements.
The selectors it builds are "semantic," so they hold up better when a page changes. Chrome DevTools' "Copy Selector" (and similar tools) usually give you something brittle like #top > div.w-100.ph0-l.ph3.ph4-m > h1 > span, which breaks with the smallest layout change. Selector Forge aims for selectors that survive those changes, for example: //div[@aria-label="Showing weekly downloads"]//p[@aria-live="polite"].
Why we built it: For the past couple of years we've been building Intuned Agent, a coding agent for browser automations. We learned fast that selectors are the most fragile part of any browser code, and that good selectors go a long way toward making automations reliable. So we split selector creation into its own agent and let our main agent call it as a tool. LLMs aren't great at this by default, so it made a real difference in the code quality.
We figured this piece is useful on its own, so we packaged it as an extension. That's what we're launching today.
A few details:
Open source (code on GitHub)
Works on Chrome and Firefox
Free for up to 200 selectors a month, unlimited on paid plans
What's next: most developers aren't writing this code by hand anymore, so we want coding agents to call it directly over a CLI or MCP. Our roadmap is on GitHub.
Links:
Site: https://selectorforge.ai/
Chrome: https://chromewebstore.google.co...
Firefox: https://addons.mozilla.org/en-US...
Code: https://github.com/Intuned/selec...
Demo video: https://www.youtube.com/watch?v=5cz6zP0zR-Q
Would love your thoughts, questions, and feedback!
The silent wrong-click after a layout shift is the failure that's bitten me, way more than a clean no-match which at least throws. You said the judge only reports back when nothing survives, so at runtime, if a baked selector quietly over-matches or grabs a different anchor after a redesign, does it surface that, or is catching the confident-but-wrong hit on the calling agent?
I like that this is aimed at resilient selectors rather than just another recorder. In browser automation the annoying bit is not capturing a selector once, it's keeping it alive after a small DOM/class change. Curious if you score candidates by stability signals like text/aria/data attrs, or mainly by replay success?
Interesting problem. For AI-generated selectors, the part I would test hardest is not the first successful selector, but how it fails after the UI changes.
A strong workflow would show: the matched element count, why the selector was chosen, what changed since the last run, and a fallback path that does not silently hit the wrong element. Browser automation failures are much safer when the tool refuses to act than when it confidently clicks a nearby sibling.
The semantic, resilient selectors are the part I would test first, since most scrapers break exactly when class names or DOM order shift. I like that it handles array selectors and not just single elements, which is where naive "copy selector" tooling usually falls apart. When the AI generates one, can I pin a specific stable attribute and have it build the selector around that, or is the output a single best-guess I have to accept or regenerate?
The part I’d want to see in practice is the failure case. When Forge rejects a selector during judging, does it show why, like over-matching, under-matching, or matching the wrong labeled field, or does it just return the best surviving option?
Brittle selectors have broken more of my scripts than I’d like to admit. Finally, something that makes them hold, love the name too.
Nice launch! One of the biggest pain points in browser automation is flaky selectors. Curious whether the AI prioritizes attributes like aria-label, data-testid, and stable text content before considering class names.
About Selector Forge on Product Hunt
“Browser extension for AI-generated resilient selectors”
Selector Forge launched on Product Hunt on June 22nd, 2026 and earned 116 upvotes and 19 comments, placing #11 on the daily leaderboard. Browser extension to create reliable CSS and XPath selectors using AI. You can use it to create a selector for a single element or for an array of elements. The selectors it creates are meant to be "semantic" and more resilient to page changes! Extension is also open source on GitHub: https://github.com/Intuned/selector-forge
Selector Forge was featured in Chrome Extensions (52.7k followers), Open Source (68.6k followers) and Developer Tools (515.9k followers) on Product Hunt. Together, these topics include over 103.4k products, making this a competitive space to launch in.
Who hunted Selector Forge?
Selector Forge was hunted by Ahmad Ilaiwi. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Selector Forge stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Ahmad Ilaiwi