found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant
jev-browser
Unofficial browser automation where the calling LLM states the outcome and Jev decides each element, action, and value from a Playwright page snapshot. Ships as a library, CLI, and MCP server.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- Ying-Kai-Liao
- Added
- 2026-09-22
Tagscommunityjavascriptbrowsermcpagentsplaywright
Highlights
- One ~300 ms System One request per round answers which element, which action, which value, and whether the step is done, blocked or erroring.
- Reported 40 of 42 tasks correct on live sites in the latest run, with zero false done claims.
- A five-step checkout measured about 14 seconds end to end, at 2 to 4 Jev calls per step.
- Handles iframes, shadow DOM, new tabs, file upload, drag and drop, 2,000+ element pages, and non-English UIs.
- The MCP surface includes browser_do, browser_check, browser_choose, browser_snapshot, browser_act, and browser_screenshot.
Quickstart
bash
npx playwright install chromium
claude mcp add jev-browser -e TYPESAFE_API_KEY=YOUR_API_KEY -- npx -y -p jev-browser jev-browser-mcpWatch out
MIT-licensed but unofficial and not affiliated with TypeSafe. Needs npx, Chromium via Playwright, and a TYPESAFE_API_KEY; ordered sub-goals or value-comparison judgments should be split or verified separately.
More like this
143GitHub stars
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.
Tools & Integrations#community#javascript#browser
Communityjev-voice-browser
8GitHub stars
Delegated browser execution for parent agents: Jev picks one bounded typed action from the current page snapshot, agent-browser performs it, and ambiguous or stuck flows escalate back to the parent.
Tools & Integrations#community#javascript#browser
Communityjev-agent-browser
17.5kGitHub stars
Browser Use's ultrafast agent: Jev picks an operation and an element from an indexed action space in one request, and a small LLM writes text only when the action is TYPE_TEXT.
Tools & Integrations#community#python#browser
Communityjev-ultrafast
From the community
Posts from builders shipping with Jev right now.
Instant compaction with Jev
A Claude session from 1M to 86K tokens
This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be Show more
found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant
Vercel's fx safety reviewer, 18x faster
We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.
@fazxes
We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice
Jev lands on OpenRouter
Jev by @typesafeai is now on OpenRouter, in beta. Jev is a System One model. Instead of generating text, it takes your app's state plus a typed question and returns a typed decision with a probability attached. There is no JSON prompting, parsing layer, and nothing to validate Show more
700 leads scored for $0.09
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
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)
