otto

Open-source native computer use for macOS and Windows: TypeSafe Jev, local OCR, and selective planning.

How it uses Jev

An open-source desktop computer-use agent for macOS and Windows . Otto combines TypeSafe Jev decisions with an optional GPT-6 Astra planner, and can apply an exact set of form values after one review without calling a model. It works through native accessibility controls and local OCR.

Getting started

Downloadable builds bundle the runtime. Native access requires OS permissions; guided tasks also require your own API keys. Current macOS packaging uses ad-hoc integrity signing, without Developer ID signing or notarization; Windows publisher signing is not configured. Read each release's notes before installing.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to otto

Browse all
jev-chat-windows project preview
Browser & computer use
Windows 微信回复助手(非官方修改版):本地离线 OCR 读屏 + 模型起草候选回复 + 一键填入微信输入框,可选自动发送。不 hook、不注入、不读微信数据库。
typesafe-computer-use project preview
Browser & computer use
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
computer_use project preview
Browser & computer use
macOS computer use driven by Jev (TypeSafe System One) as the decision maker
pi-jev (iefnaf) project preview
Agent tooling
Pi extension suite powered by Jev: selective context compaction and model routing
jev-chat-windows-deepseek-jev project preview
Windows 微信回复助手:DeepSeek 官方生成话术,TypeSafe JEV 官方判断排序,支持可取消的 3 秒自动发送。
jev-notion project preview
Demos & playgrounds
🚀 Blazing-fast native macOS menu bar companion for Notion. Pure Swift & SwiftUI (<3MB), 8 languages.
jev-benchmarks project preview
Benchmarks & research
Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.
jet project preview
Benchmarks & research
A TypeSafe-native (Jev) coding agent built on Recursive LLM Context Decomposition (RLCD), with a native macOS client
jev-mac-voice project preview
Applications
English full-duplex voice control for macOS with OpenAI Realtime, native Accessibility, and Jev.