Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type (this video is at 1x speed btw) Built a tiny open source browser agent. try it below ↓
Agents & browsers
85 builds · page 1 of 3
# Jev: AI Decisions as a Typed Function Call What I learned using TypeSafe's Jev for code review, and why its more surprising uses are browser control and generative UI.…
ResourceAgents & browsers
Jev: AI Decisions as a Typed Function Call | StackToHeap
Chrome extension that labels every post you scroll past on X with six typed questions per post, and counts what it costs in the corner.
GitHubAgents & browsers
x-scanner
Chrome extension that scores draft posts and reply context before posting; optional media descriptions come from a separate vision model.
GitHubAgents & browsers
Vibe Check for X
Chrome extension that asks Jev whether each DOM element is an ad and removes the ones that are.
GitHubAgents & browsers
TypeSafe AdBlock
Browser extension that filters your X timeline by plain-language rules, with Jev as the default classifier.
GitHubAgents & browsers
Sharp
A three-dimensional reference gallery over The Met, NASA, Cosmos, and the Prelinger Archives, with Jev choosing the search phrases.
GitHubAgents & browsers
RefGarden
Say a command and it runs as AppleScript, or say a web task and it drives Chrome.
GitHubAgents & browsers
macbrow
Coding-agent skill that drives Chrome over CDP to look for jobs on company sites, with Jev scoring pages and links.
GitHubAgents & browsers
JevScout
ACP and MCP adapter that pairs Jev with any LLM agent, including Codex, Claude, Grok, and OpenCode, for typed decisions and computer use.
GitHubAgents & browsers
Jevbridge
Local Instagram and TikTok research app where Jev selects a platform and bounded socai operation from observed state, while code enforces confidence and the socai CLI executes…
GitHubAgents & browsers
jev-social
Browser extension that reads the YouTube caption track and paints a per-segment sponsor probability on the seek bar before the intro ends, with no crowd database; reports…
GitHubAgents & browsers
jev-skip
Config-driven inbox classifier that tags, moves, flags and notifies from typed answers.
GitHubAgents & browsers
jev-mail-classifier
Codex computer-use skill where Jev picks the next element and action from on-screen text, with a local policy gate for sensitive steps.
GitHubAgents & browsers
Jev-cu
Local whisper.cpp for the transcript, then one Jev request picks the action and its typed arguments; code owns execution.
GitHubAgents & browsers
Jev Voice
Local browser app that turns batched per-pixel Jev distributions into paintings; prompts describe pixels and regions rather than sending raw images.
GitHubAgents & browsers
Jev Paint
Native macOS GUI automation on Apple silicon: OmniParser CoreML and Apple Vision OCR identify controls locally, Jev selects the action.
GitHubAgents & browsers
Jev macOS Loop
Unofficial Chrome extension (Manifest V3) port of Jev Ultrafast: Jev picks the operation and DOM element in one request, a small text model writes typed values, and it runs in…
GitHubAgents & browsers
Jev for Chrome
Interactive playground that walks through a typed request and its probabilities, with your own key.
GitHubAgents & browsers
Jev Explained
Chat-style command bar where Jev picks the tool, arguments, and reply type, and code builds every reply from tool data.
GitHubAgents & browsers
Jev Chat
GitHubAgents & browsers
Jev Browser
Bundle of skills that hand an agent's small decisions to Jev: model routing, skill selection, retrieval filtering, compaction, and computer use, with a routing dashboard.
GitHubAgents & browsers
Hermes Jev Skills
Classifies a Grok Bot request before expensive research, browser, retry, or subagent work, so it can reuse a fresh artifact or stop a failing retry.
GitHubAgents & browsers
Grok Bot Jev Router
macOS workspace for Codex where Jev finds past sessions and the decisions made in them.
GitHubAgents & browsers
Cheshi
Zero-lock, session-preserving Chrome MCP server that couples a local Jev System One semantic micro-loop (`chrome_act_toward_goal`) with an 85%+ pruned DOM tree (Shadow DOM &…
GitHubAgents & browsers
BrowserClaw
GitHubAgents & browsers
agent-desktop
We just ran Jev on our WebMCP benchmark. The result: basically broke the benchmark. Jev + Mercury 2.5 (a fast, low-cost LLM) using WebMCP solved 100% of the tasks at roughly 112× lower model cost than GPT-6 Astra using computer use with code execution. Compared to Astra using
we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand
Okay so Jev can actually do computer use really well Without any screenshots, or LLMs and no Pixels leave my mac I dont even read the Dom elements A local CoreML model segments every button and UI element on screen. On-device OCR reads the labels. That text is all Jev gets.
X postAgents & browsers
Computer use without screenshots
got @typesafeai's new model Jev as a chief of staff for bots Jev reads the task, wakes the right teammates off the bench and gives each one the right model It is possible on OpenMausBot as it supports all the LLMs from your existing subscriptions Jev as a decision engine is
X postAgents & browsers
A chief of staff for bots
X postAgents & browsers
An agent with a Jev model router
Acabo de terminar la implementación de @typesafeai + Chromium Headless para que mis agentes puedan navegar por internet a una buena velocidad! En este ejemplo le pido al agente que entre a la página del término "Café" en Wikipedia y navegue por los hipervínculos hasta terminar
X postAgents & browsers
Headless Chromium agent
GitHubAgents & browsers
jev-voice-browser
Claude me integró Jev con Playwright para buscar usados. Lee unos 26 artículos por minuto y decide qué hacer con cada uno en 406 milisegundos Descartó los que no encajaban con lo que busco, ofertó por los que sí y hasta les mandó un mensaje a los vendedores cuando faltaba algún
I built a chat bot with jev, no LLM at all! Responses are instant, no hallucinations. I hooked it up to web search, wikipedia, weather, todoist and home assistant. Jev decides what tool to call and what args to use based on the prompt. Instant answers cite sources as well!
X postAgents & browsers
A chat bot with no LLM
I built a Chrome extension for agentic browsing using Jev by @typesafeai, https://t.co/Xa9toMieqT including AI Gateway by @vercel. Now agents can browse, click, and interact with websites directly in your browser. Cost effective and fassst. Decision-making by Jev.
X postAgents & browsers
Agentic browsing in Chrome
Jev made our Slack agent 2x faster ⚡️ Our agent can be quite slow because it needs to read skills and figure out which tools to call. We used @typesafeai's new model to speed this up by first passing it the prompt and classifying the best skill, tool and params to use before
I built a voice controlled computer-use for my mac using @typesafeai's Jev and it's INSANE how fast it is! I can dictate "open the notes app and create..." and the app opens before I even finish my sentence.
X postAgents & browsers