Jev Ultrafast
A browser agent that turns a single goal into a sequence of lightning-fast actions.
Browser, desktop, and mobile automation with Jev choosing the action. Browse the collection in Jev Library.
59 entries in the current community snapshotA browser agent that turns a single goal into a sequence of lightning-fast actions.
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
Jev-powered element selection for your agent’s existing computer-use tools
WXT browser extension: Jev-powered page clutter removal with reusable template rules.
An Android agent powered by Jev decisions, with a live studio to watch every step.
TypeScript browser agent for ego lite: Jev Ultrafast indexed actions, TypeSafe Jev decisions, persistent observe/act CLI. No Chrome or Playwright.
Parallel web search for terminals and agents, with local Chromium and Jev-guided exploration.
Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.
macOS computer use driven by Jev (TypeSafe System One) as the decision maker
Chrome extension that re-ranks Google results with TypeSafe Jev and folds away sales pages and SEO filler.
Almond-fastloop: Almond's browser computer-use rig (Chrome DevTools + TypeSafe Jev), and the Browser Use Olympics benchmark it is measured on.
Fast structured Android control loops with TypeSafe Jev and Mobile MCP
Browser Use Olympics by Almond: one prompt, five events, one clock. Plus fast loop, a ~200-line browser computer-use agent (Chrome DevTools + TypeSafe Jev).
Jev-powered semantic browser use
Open-source Chrome extension that filters AI-generated prose and ads with Jev
A Chrome extension that brings TypeSafe's Jev to X.com to analyze posts as you browse
One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions.
Jev-powered browser MCP for LLM agents — ~300ms decisions, no LLM tokens in the loop. Benchmark vs Playwright MCP included.
Jev-augmented Playwright MCP proxy — page-state triage, prompt-injection shielding, goal-based snapshot pruning, risky-action gating. Drop-in wrapper around @playwright/mcp for any coding agent.
Local browser automation UI that uses TypeSafe Jev to choose bounded page actions and a text model only for field values.
Open-source native computer use for macOS and Windows: TypeSafe Jev, local OCR, and selective planning.
Bounded exploratory browser testing with Jev, deterministic assertions, and replayable evidence.
Drives a real browser with Jev making every decision and Vercel's agent-browser performing every action, with a benchmark.
Hybrid browser harness: an LLM turns goals into verifiable subgoals, Jev chooses each action and DOM field, Playwright acts.
Browser use using Typesafe's Jev model
🧹 Fun project: a Chrome extension that asks a tiny AI decision model (TypeSafe Jev) "is this DOM element an ad?" and pops it off the page. BYOK, no backend, not a real ad blocker.
Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.
5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.
ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.
2D autonomous car simulation in the browser, driven by TypeSafe's Jev decision model
AskJev — Jev autopilot for any website + guard on irreversible clicks (TypeSafe System One, not Claude)
在 X 的时间线上,给每条帖子标出它想让你干什么。判断来自 Jev,一个只返回概率、不生成文本的模型。
Privacy-first Chrome extension that semantically blocks native ads, sponsored feed cards, and video ads using TypeSafe Jev
Evidence-driven frontend QA built on Jev Ultrafast and Browser Harness, with a synthetic todo demo.
Chrome extension: vibe-check your X posts with TypeSafe's Jev before you hit Post
Chrome extension that labels every post you scroll past on X with typed Jev judgments and a live cost counter
The first general-purpose System One agent for Jev
Jev-powered social media research through the socai CLI
Data extraction for systematic reviews, quoted from the papers. Ask a trial report and its supplements your extraction form or a RoB 2, ROBINS-I, QUADAS-2 or TIDieR template; Jev points at the lines, every answer is a verbatim quote with its page, you check it and export the table. Files stay in your browser.
Browser automation with Jev (TypeSafe) as decision model
Chrome extension that labels every post on X (Substance · Humor · Chit-chat · Promo · Junk · AI-written) with TypeSafe Jev, and hides the ones you don't want.
Pure Jev that can "type" and drive towards task completion.
JevArena — two Jev agents duel in click-only browser games (Browser Use + TypeSafe Jev)
JevNoiseGate filters unwanted notifications and SMS on Android. Rather than matching keywords, an LLM decides what's noise — and only what it explicitly flags is blocked. Verification codes are matched on-device and never uploaded; anything uncertain passes through.
Türkçe ve İngilizce doğal konuşmayla Windows 10/11 bilgisayar kontrolü: OpenAI Realtime, local Whisper, Jev, UI Automation ve Playwright.
Write Cucumber tests with just the .feature file. No step definitions — Jev (TypeSafe AI) resolves each Gherkin step and Playwright runs it.
Browser use for coding agents, 3-5x faster than browser-use. MCP server + CLI; TypeSafe Jev decides every step in ~300 ms.
Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
Jev for Chrome: drives the tab you are looking at with TypeSafe Jev, a sub-second decision model. Community port of browser-use/jev-ultrafast, not affiliated with TypeSafe.
Practical, tested recipes for TypeSafe's Jev decision model on OpenRouter: support triage, database indexing, file organizing, tagging, taxonomies, dedupe, PII detection, extraction, search re-ranking and a browser agent.
Hand the browser work off: an MCP server where a decision model drives the page for your agent, so a flow costs one tool call instead of a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay. Speaks CDP to your Chrome.
Aside agents decide with TypeSafe Jev (System One: Choice/Score/Noul). Not a Cua binding — Jev is the model, Aside is the browser runtime.
Chrome extension that triages Gmail with TypeSafe's Jev model: category, priority, spam % and reply % on every email.
A Chrome extension that covers distracting YouTube videos with Jev. Show anyway whenever you want.
A browser form for building requests to TypeSafe's Jev: pick a template, fill in the blanks, copy the request. No JSON, no install, runs locally.
Know before you click. A Chrome extension that reads articles and YouTube videos ahead of you and says read, skim, save, or skip — with a confidence, tuned to your goals. Open source, MV3, powered by Jev.
Validated enhancement pack for MiniMax Code CLI on arm64 DGX Spark + local GLM-5.3-EXL3: TUI scrollbar + context-meter patches, compaction repair for local vLLM, Jev Ultrafast + Playwright MCP browser integration, real usage ledger.
Non-Autoregressive AI Agent Decision Model. Open-source SOTA alternative to TypeSafe Jev. O(1) Tool Routing & DOM Automation on Qwen3.5-2B .
Browser-only playground for Jev (TypeSafe AI's decision model) via Vercel AI Gateway