This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
ego-jev
Jev inner loop for ego lite — 0.4s per DOM step
Browser agents usually spend a whole LLM turn — screenshot plus reasoning — just to click one element. ego-jev swaps that for a Jev (TypeSafe System One) inner loop inside ego lite: number the page's interactive elements, one typed call picks the operation and its target, ego executes. ~0.4s per step, no screenshots, no free text. Login and payment escalate back to you. MIT.
Hi PH — I built this after watching browser agents burn a full LLM turn per click. jev-ultrafast (github.com/browser-use/jev-ultrafast) proved the loop standalone; ego-jev brings it into ego lite so the agent keeps your real browser, sessions and logins.
Install: npx skills add ZephyrDeng/ego-jev
Needs: ego lite + a TypeSafe or AI Gateway key. About $0.0005 per step.
No key handy? scripts/selftest.mjs runs the loop offline with a mock decider.
Happy to answer anything — and curious where the guard rails should go next.
About ego-jev on Product Hunt
“Jev inner loop for ego lite — 0.4s per DOM step”
ego-jev was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #126 on the daily leaderboard. Browser agents usually spend a whole LLM turn — screenshot plus reasoning — just to click one element. ego-jev swaps that for a Jev (TypeSafe System One) inner loop inside ego lite: number the page's interactive elements, one typed call picks the operation and its target, ego executes. ~0.4s per step, no screenshots, no free text. Login and payment escalate back to you. MIT.
On the analytics side, ego-jev competes within Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1M followers on Product Hunt. The dashboard above tracks how ego-jev performed against the three products that launched closest to it on the same day.
Who hunted ego-jev?
ego-jev was hunted by 老毛. 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.
For a complete overview of ego-jev including community comment highlights and product details, visit the product overview.
老毛