jev-skip
浏览器扩展,使用 Jev 从 YouTube 字幕中识别可能的赞助片段。
Browser extension that uses Jev to identify potential sponsor segments from YouTube captions.
EXPLORE JEV
浏览网页自动化、DOM 操作、OCR 与电脑控制项目,比较它们的输入和执行方式。
THE RESOURCE INDEX
项目、工具、教程与文章
原始链接,按用途整理。
支持中文与多关键词,例如:浏览器 DOM。
全部资源
浏览器扩展,使用 Jev 从 YouTube 字幕中识别可能的赞助片段。
Browser extension that uses Jev to identify potential sponsor segments from YouTube captions.
浏览器自动化工具,由 Jev 选择操作与 DOM 元素,由语言模型生成输入文字;需要 Python 3.12+、Chrome、Jev 与文字模型服务。
Browser Use's ultrafast agent: Jev picks the operation and DOM element in one request; a small LLM only writes text when typing is needed.
利用 OCR 识别的文字帮助 Jev 选择电脑操作。
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
Standalone Android agent for Mobilerun where Jev makes every decision, with a live React studio and an Uber demo.
WXT browser extension: Jev-powered page clutter removal with reusable template rules.
Jev-powered element selection for your agent’s existing computer-use tools
Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.
Hybrid browser harness: an LLM turns goals into verifiable subgoals, Jev chooses each action and DOM field, Playwright acts.
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.
Almond-fastloop: Almond's browser computer-use rig (Chrome DevTools + TypeSafe Jev), and the Browser Use Olympics benchmark it is measured on.
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.
Open-source native computer use for macOS and Windows: TypeSafe Jev, local OCR, and selective planning.
Drives a real browser with Jev making every decision and Vercel's agent-browser performing every action, with a benchmark.
Chrome extension that re-ranks Google results with TypeSafe Jev and folds away sales pages and SEO filler.
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).
Open-source Chrome extension that filters AI-generated prose and ads with Jev
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.
Bounded exploratory browser testing with Jev, deterministic assertions, and replayable evidence.
Browser & Computer-Use Agent Optimized for Social Media: Research, Content Extraction, and Agentic Analysis
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.
Evidence-backed index of real-world Jev (TypeSafe AI System One) use cases, cookbook, how-to, repos, patterns, and measured results
Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground
2D autonomous car simulation in the browser, driven by TypeSafe's Jev decision model
Local reproduction of AlexWortega/openjev (Qwen3.5-4B NLI cross-encoder playing Doom), plus real-time headed play and a browser front-end
Evidence-driven frontend QA built on Jev Ultrafast and Browser Harness, with a synthetic todo demo.
AskJev — Jev autopilot for any website + guard on irreversible clicks (TypeSafe System One, not Claude)
Browser decision playground and reproducible experiments on memory, uncertainty, and Doom control
JevArena — two Jev agents duel in click-only browser games (Browser Use + TypeSafe Jev)
浏览器自动化工具,由 Jev 选择操作与 DOM 元素,由语言模型生成输入文字;需要 Python 3.12+、Chrome、Jev 与文字模型服务。
Public Grok skill snapshot around Browser Use Jev Ultrafast
Hyprland/NixOS fork of typesafe-computer-use — grim + hyprctl + ydotool, TypeSafe Jev decisions
Testing TypeSafe's Jev model on real-time browser games (flappybird.io, play.tetris.com)
Reproducible text-first browser automation experiment with TypeSafe Jev and Playwright.
A macOS computer-use agent with a dynamic, indexed action space. No screenshots, no coordinates. A macOS port of browser-use/jev-ultrafast.
Browser-only UI for icon-matcher — paste a TypeSafe.ai key, match a UI title to an icon live, no backend.
Browser Tetris with a first-class AI API: play it with a built-in planning agent, TypeSafe's Jev decision model, or any OpenAI-compatible chat model
Curated list of projects built on TypeSafe's Jev model, read before listed. With media and our own measurements. Not affiliated with TypeSafe AI.
An agent in the browser that pays for thinking once: author a deterministic spec (Jev first, LLM on escalation), replay it for 0 tokens.
Agent plugin: TypeSafe Jev browser automation skills for Grok Bot / Cursor
A browser agent with no LLM in the loop — deterministic code plus Jev, a System One model. ~118ms per decision, typed and auditable.
试试项目英文名、相关用途,或重置筛选。
部分项目补充了中文用途说明,原始描述保留供对照。在 GitHub 阅读完整目录 ↗