Skip to content
JevDirectory.org
CommunityTools & Integrations72 starsVerified 2026-09-22

Jev Voice

A hands-free macOS voice assistant: whisper.cpp transcribes locally in about 100 ms, then one roughly 250 ms Jev request selects a typed action plus arguments, and code executes it against the Mac.

Open github.comkevinbadi/jev-voice
Category
Tools & Integrations
Published by
Community
Author
kevinbadi
Added
2026-09-22
Tagscommunitypythonvoiceagentscomputer-use

Highlights

  • Pipeline: mic, energy VAD, whisper.cpp on Metal (~100 ms), one Jev request (~250 ms), then macOS actions and spoken replies via say.
  • Handles opening apps, site-specific search, typing, about 45 keyboard shortcuts, scroll-wheel events, volume and media keys, and compound commands.
  • Multi-step tasks port the jev-ultrafast agent loop from the DOM to the macOS Accessibility tree, offering only operations with a valid target.
  • Before input the executor re-reads the target's role, label, value, and enabled state, and hit-tests its centre so a covered control is never clicked.
  • Everything runs locally except the Jev call; code produces candidate values and Jev selects rather than generating text.

Quickstart

bash
cp .env.example .env
./scripts/setup.sh
jev --text "open chrome and go to youtube" --dry-run

Watch out

MIT-licensed; requires macOS on Apple Silicon with whisper-cpp, ffmpeg, uv, and a TypeSafe API key, plus Microphone, Accessibility, and Input Monitoring permissions.

More like this

typesafe-computer-use
799GitHub stars
A macOS computer-use loop that OCRs the screen, asks Jev for the next action with typed Choices, and clicks, at about $0.0002 per decision without sending screenshots to a frontier model.
Tools & Integrations#community#python#agents
Communitytypesafe-computer-use
Jev Ultrafast
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
MemSearch
2.6kGitHub stars
A cross-platform memory layer for AI coding agents: conversations from Claude Code, Codex, DeepSeek Harness, OpenClaw, and OpenCode become Markdown memories indexed in Milvus, with optional Jev reranking through the TypeSafe API.
Tools & Integrations#community#python#agents
Communitymemsearch
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Six uses that stuck after 60 days

Security decisions that fit Jev

Kostas
Kostas
@Kostastsale
·

This made me rethink where AI actually fits into security engineering. For purely engineering work, forget about ChatGPT or Claude. TypeSafe AI just released Jev, and I think it’s going to change how we build AI into security workflows. Instead of asking an LLM to “investigate Show more

TypeSafe AI
TypeSafe AI
@typesafeai

we are officially out of stealth! join the frontier and get access to Jev on our website (link on profile)

Reply
Read 14 replies

A million judged questions

Inferring Jev's internals from 1,000 calls

iwashi / Yoshimasa Iwase
iwashi / Yoshimasa Iwase
@iwashi86
·

Jevの内部アーキテクチャを推測している技術記事(Jev’s Architecture Unmasked)からメモ。 ・本記事はJevのAPIを約1万回の呼び出して、内部構造を推測したもの ・従来の言語モデルを用いた分類やルーティングでは、トークンを1文字ずつ逐次生成するために膨大な無駄な計算コストが発生していた。 Show more

Reply
Read 2 replies

The open System One roundup

小墨同学
小墨同学
@xiaomovps
·

Jev 发布没几天，开源社区已经开始疯狂复刻了🔥 最值得推荐的五个模型： 1、Laya 421M：原生决策模型，支持 Mac 2、Decider-2B：最像 Jev，基于 Qwen3.5 3、NanoJev 0.6B：专门的 Decision Head 4、Reflex：Qwen3.5 + Direct Logits 5、System-One 4B：专门做概率校准 Show more

小墨同学
小墨同学
@xiaomovps

Jev 刚发布没几天，开源社区就出现了同款🔥 Decider-2B模型，是基于 Qwen3.5-2B 做了特殊调整 它和 Jev 模型是一样的 只做选择 评分和判断 不是文本类的 LLM 模型 但两者还是有几个明显区别： 1、模型 Jev：闭源 System One Model Decider：Qwen3.5-2B，约 1.9B 参数，Apache 2.0 开源 2、价格

Image
Reply
Read 6 replies

The launch post