The Android assistant reads visible conversations through accessibility and local OCR, displaying analysis and reply suggestions in an overlay. Jev judges intent and response choices; a generative model drafts three candidates and Jev ranks them.
Computer & desktop use
Desktop automation projects that read the screen or accessibility tree and act on native applications. Jev decides the next action and target.
140 active projects match this task, ordered by traction. Browse other tasks →
PyGPT is a multi-provider desktop assistant for Linux, Windows and macOS, with chat, agents, RAG and tool integrations. The Jev plugin exposes jev_evaluate(state, questions), returning Choice, Score or Noul results to the current model.
typesafe-computer-use turns a written goal into desktop actions using OCR and accessibility controls on a Mac. TypeSafe Jev chooses the action, target and site; code supplies facts, while a separate writer handles free text. Provide a TypeSafe key and screen-recording and accessibility permissions. The CLI offers a dry run before real mouse and keyboard control.
Reticle checks running apps using network, console and state evidence, returning pass, fail or unknown. The optional Jev exploration driver selects DOM candidates; internal verification-flow routing remains planned. Connect a development app through MCP, describe expected behavior and save flows for deterministic replay.
ollaya downloads named open decision models and serves typed questions through a local daemon. It implements TypeSafe-compatible endpoints for existing Jev clients, while remaining an independent project. Use its CLI, desktop app or MCP server; Modelfiles can package reusable question sets.
DSCODE is a macOS coding agent whose terminal interface, CLI and scripts share a persistent session runtime. The repository includes a separate Jev client for OpenRouter’s alpha Decisions endpoint, supporting Choice, Score and Noul. Use sessions for editing, tests and agent handoffs; the Jev client requires an API key.
Jev Browser Use delegates navigation, clicks, toggles and scrolling while Codex handles text entry and final verification. Jev selects actions from observed controls using accessibility text; the existing Computer Use connection executes them. Requires Node.js 22+, a connected Codex browser and matching TypeSafe or OpenRouter credentials.
TipTour is a macOS menu-bar companion with Jev text tasks and a separate Gemini voice mode. Jev chooses locally detected controls; TipTour executes and validates clicks while screenshots stay local. Select a mode, supply its API key and grant permissions; building requires macOS 14.2+ and Xcode.
The floating chat panel displays intent and risk judgments and candidate replies that users can copy or insert into the chat input. Use an Apple Silicon Mac with macOS 13 or newer. Grant Screen Recording for screenshot-based reading and Accessibility for text access or insertion, then choose judgment and generation providers in settings.
Jev Codex Router chooses model capability and thinking effort for each Codex model call, including tool continuations. Use the documented macOS setup with Codex desktop, Node.js, Python and a TypeSafe key, then install the embedded stack and select its router.
Say it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model
Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.
TypeSafe Jev action selection inside Codex Computer Use
ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.
Voice and text control for macOS. One floating bar, live UI action selection with Jev, and a continuous observe–act–verify loop.
TypeSafe Jev controls original StarCraft shareware through keyboard and mouse with recorded action probabilities.
Open-source macOS AI computer use and native GUI automation on Apple silicon. Jev + OmniParser CoreML + Apple Vision OCR. Bring your own OpenRouter, Vercel AI Gateway, or TypesafeAI token.
MCP server for TypeSafe Jev: typed classify, score, check, match and screen for any agent, with confidence on every answer
Fast browser and macOS computer use for MCP agents. Local execution, TypeSafe Jev decisions, verified outcomes.
Voice control for macOS that acts partway through your sentence, built on Jev (TypeSafe)
Jev-powered conversation memory: find past sessions and revisit decisions with original sources. A macOS workspace for OpenAI Codex. Manage AI conversations and agents, explore code with CodeGraph, and work with Git, Ghostty terminals, and Apple Notes in one app.
Linux, macOS ve Windows için kaynaklı ikinci beyin. Claude Code, Codex ve Antigravity adaptörleri; yerel Markdown kasa, ayrı hafıza incelemesi, isteğe bağlı Mem0/Jev.
Jev for Computer Use
Jev judgment, not generation: prune long tool output, screen fetched pages for injected instructions, and gate completion claims inside DeepSeek Harness.