Skip to content
JevDirectory.org
CommunityTools & Integrations87 starsVerified 2026-09-22

jev-use

Voice and typed computer use for macOS: Jev picks the next on-screen action from the Accessibility tree, macOS performs it, and each step is checked for its real effect. No screenshots are sent.

Open github.comsavka777/jev-use
Category
Tools & Integrations
Published by
Community
Author
savka777
Added
2026-09-22
Tagscommunityswiftmacoscomputer-useagents

Highlights

  • Each step walks the front app's Accessibility tree in about 120 ms, then sends one jev-latest request with the goal, numbered targets, and last ten actions.
  • A loop takes about 0.3-1.5 s per step and ends on DONE, BLOCKED, or WAIT; low-confidence and destructive picks stop and ask instead of acting.
  • Reads the screen without screenshots, excludes secure text fields, and sends the command, app and window names, targets, labels, values, and recent actions.
  • Requires macOS 14.2+ and Xcode with no dependencies; the API key is stored in the Keychain, and builds run through bash build.sh.
  • Supports hold-to-talk with a configurable shortcut, an optional 'Hey Jev' wake phrase, a hands-free widget, and typed commands.

Quickstart

bash
bash build.sh
open "$HOME/Applications/Desktop Voice.app"
scripts/say.sh "Open Finder"

Watch out

MIT-licensed and macOS-only. Needs macOS 14.2+, Xcode, a TypeSafe key, and Accessibility, microphone, and speech permissions; speech uses Apple Speech, which may process audio online.

More like this

TipTour
648GitHub stars
A macOS menu bar app that turns a typed click task into desktop actions: Jev picks from locally detected controls, TipTour executes and validates each action, and a separate Gemini mode handles voice.
Tools & Integrations#community#swift#macos
Communitytiptour-macos
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 Voice
72GitHub stars
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.
Tools & Integrations#community#python#voice
Communityjev-voice
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

LLM-as-a-judge, sped up

Yuchen Jin
Yuchen Jin
Databricks
@Yuchenj_UW
·

Jev has spoken. It picked which model is AGI. 20–200x faster. 40–400x cheaper. This could make things like LLM-as-a-judge insanely fast and nearly free. (I tried a bunch of prompts and still didn’t burn through $0.10.)

Image
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read 94 replies

Instant compaction with Jev

A Claude session from 1M to 86K tokens

Alex Volkov
Alex Volkov
CoreWeave
@altryne
·

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

Image
Image
tamara
tamara
@tamarajtran

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

Watch on X
Reply
Read 164 replies

Vercel's fx safety reviewer, 18x faster

Guillermo Rauch
Guillermo Rauch
Vercel
@rauchg
·

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.

Pranit
Pranit
Vercel
@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

Image
Reply
Read 137 replies

Jev lands on OpenRouter

700 leads scored for $0.09