jev-use for computer use
A Cua Driver integration that uses Jev to choose bounded computer actions on macOS, Windows and Linux.
ACTION SELECTION
Jev choosing the next click, key or app action from a bounded action space built out of the DOM, OCR or an accessibility tree.
Development previews and demos of Jev picking the next action in a browser or desktop loop.
A Cua Driver integration that uses Jev to choose bounded computer actions on macOS, Windows and Linux.
Speech becomes text, the DOM becomes an action catalog and Jev chooses the next click.
A Mac begins executing a selected action while the user is still speaking.
A calendar task compares a Jev-based action loop with built-in computer use.
A Marketplace plugin connects a Cline desktop app to Jev through Vercel AI Gateway.
Voice is mapped to bounded Figma actions, with Jev choosing the operation.
Many browser scenarios run in parallel with Jev serving as a low-cost evaluator.
A 706K-parameter form-filling specialist is compared with Jev on a narrow evaluation.
A computer-use agent that OCRs the screen, asks Jev to pick the next action, and clicks; the author says the loop generalizes across operating systems.
The accessibility tree becomes the state and possible actions become questions; Jev picks the next step in a Stagehand-driven browser.
A WXT browser extension that asks Jev whether page elements are clutter (ads, cookie banners, upsells), then saves reusable per-template hiding rules; sends snippets rather than full pages, bring your own key.
A browser extension that asks Jev, per post, whether it matches a plain-language filter and collapses the ones that do; framed by the author as a content firewall.
A browser agent where Jev picks the operation and target element from a numbered element table each step, and a small LLM is called only when text has to be typed.
A mobile agent that drives a real Android device through Mobilerun with Jev choosing actions; the README states the limits of the demo itself.
A preview of browser automation for OpenCode powered by Jev plus its browser-use CLI, framed around speed; the demo video sits in Neriousy's post and dax's root post.
Coverage of browser-use/jev-ultrafast: a numbered element table per step, Jev picks action and target, an LLM only for typed text, with the project's listed limitations.
A Chrome extension that labels posts in the X timeline with Jev across five dimensions while scrolling.
A browser extension (and web version) that classifies the news article you are reading by political framing, article type, topic and how loaded the language is, using Jev as a fast probabilistic classifier.
An open-source macOS pointer companion driven by Jev or Gemini Live: a local OmniParser build on CoreML reads the screen, Jev picks where the pointer goes, Ctrl+K takes a typed task. Bring your own keys.
A browser skill that takes a website and a task, opens the browser and lets Jev decide every click from what is on screen. Video demo; the code is shared inside the club's community rather than publicly.
Say it and the Mac does it: the loop reads the accessibility tree, asks Jev which element to act on, acts, repeats — deliberately naive, no screenshots, no vision model.
A Chrome extension that labels every post on X (Substance, Humor, Chit-chat, Promo, Junk, AI-written) plus an AI-probability score, and folds the ones you don't want.
Tell the extension what you are working on; Jev checks every open tab at the door in a single call and shows the freeloaders out.
A Chrome extension that uses Jev to estimate a page's purpose and the writer's position (ad, testimonial, explainer…) and colour-codes Google search results accordingly.
An open-source Codex skill: install it, set a Jev API key, and Codex drives desktop apps with Jev making the per-step calls — the author reports the biggest gains on tasks with frequent checks and tool calls.
A computer-use assistant driven entirely by decision models: sub-second latency, near-zero cost, and it decides what to type without calling an LLM.
A Rust runtime that lets any agent operate desktop apps through their real UI structure (OS accessibility trees) with stable element refs, from the author of the hook-based routing demo.
Browser automation split in two: an LLM plans the task, Jev makes the concrete in-page choices; shipped as a library, a CLI and an MCP server.