JEV is INSANE. We gave it 700 high-intent leads and personalised outreach messages. In 40 seconds, it predicted how each message would perform, assigned a confidence score and detected lead-message mismatches. All for just $0.09. JEV can also score leads, analyse buying Show more
voice-browser
Control a headed Chromium window by voice: one Jev request per partial transcript decides intent, target, and completeness in roughly 300 ms, while code applies thresholds and builds the action.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- moritzkremb
- Added
- 2026-09-20
Tagscommunityjavascriptbrowservoiceplaywright
Highlights
- One Jev request per partial transcript with 9 to 11 typed questions, replying in about 250 to 350 ms.
- Actions: navigate, search, click, type, scroll, history, tabs, confirm, and cancel.
- Ambiguous targets get numbered page overlays, and a spoken number picks one without a model call.
- Destructive clicks require a spoken confirmation before the action fires.
Watch out
Requires Chrome or Edge for the Web Speech API (Firefox and Safari are unsupported), Node 20 or newer, and a TypeSafe key.
More like this
A browser-use agent where Jev picks one action per step from a page's interactive elements. Runs as an MCP server, CLI, or library and returns a step trace, screenshot, and console errors.
Tools & Integrations#community#typescript#mcp
Communityjev-browser
Grep by meaning instead of regex: Jev scores every line, meanings combine with AND, OR, and NOT, and one query matches across Japanese, French, German, Spanish, and more.
Tools & Integrations#community#javascript#cli
Communityjev-semgrep
Browser Use's Ultrafast agent puts Jev in charge of picking each browser action from a dynamic DOM action space. The author reports a flight search in 7 seconds for about $0.0039.
Tools & Integrations#community#x#video
Community
From the community
Posts from builders shipping with Jev right now.
700 leads scored for $0.09
Beating Gemini Flash Lite on an eval
Ran @typesafeai's Jev against an existing classifier eval that previously used Gemini 2.5 Flash Lite. It won both on quality (saturated the eval) and speed (6x)
