Desktop and mobile control with decision models

Native macOS agent app wiring 23 LLM providers into a task loop, listed with an optional Jev command-risk advisor via a TypeSafeKit client.

Rust MCP server for desktop control via accessibility trees, with an optional decision model (Jev or compatible) for small choices.

macOS menu-bar Swift app that turns on-device transcribed speech into Jev typed decisions and macOS actions, confirming hard-to-undo steps.

Rust CLI for desktop computer use via accessibility trees, with optional jev-desktop scripts letting Jev pick the control and action.

macOS computer-use package: a background app driver for any agent, plus a loop where Jev picks each UI action for a bounded subtask.

Lets coding agents run whole goals in your signed-in Chrome on macOS in background tabs, asking Jev or Claude Haiku only for real choices.

Computer-use platform (Cua Spaces, Driver, Lume) with CUA-S1 small decision models and a preview jev-use example for bounded actions.

Local stdio MCP server that executes whole browser and macOS goals with a Jev-driven observe-decide-act loop.

Verified computer-use agent: a Jev guard checks claimed completions and gates irreversible actions; Jev also takes simple steps.

Runs Intern-Decision-0.8B on Apple Silicon behind a local /v1/systemone endpoint that accepts screenshots for agent decisions.

Native macOS computer-use loop: local OCR and accessibility find controls, Jev picks the next action from a finite list.

Browser Use's browser agent where Jev picks an operation and page element in one request and a small LLM only writes text to type.

MCP server that lets agents observe and control Android phones over ADB, with Jev picking controls and judging goal completion.

Python decision layer for browser and desktop automation: code observes, acts and verifies; the model makes one typed choice per step.

Browser and computer use for coding agents via CLI and MCP, with Jev's calibrated judgments and a code-owned control loop.

Codex plugin adding a bounded Jev decision loop to Computer Use for browser tabs and native macOS apps.

Windows MCP server and CLI where Jev observes windows and chooses controls so agents can hand off whole desktop tasks.

Claude Code plugin that runs tap scripts on iOS or Android and has Jev judge each checkpoint's on-screen claims for a pass/fail verdict.

Durable Android sub-agent: a SQLite-backed worker observes the UI and Jev picks among valid actions, with verification and escalation.

Fork of mobile-mcp that adds OCR and lets Jev pick which recognised text element to tap on Android and iOS devices.

Fast iOS Simulator and Android navigator built on sim-use where Jev picks each tap instead of a frontier-model turn.

Flutter integration-test package where Jev picks the next registered UI action and judges whether the test goal is reached.

Open-source desktop browser agent where a language model plans, Jev chooses the executable action and Chromium carries it out.

Plain-English end-to-end tests for Android and iOS apps where Jev works out the taps and a lockfile replays every decision exactly.

Voice assistant daemon for Hyprland Linux desktops that acts through tool modules, with Jev gating which requests and actions proceed.

Focus mode for Omarchy/Hyprland that has Jev judge each screen against your declared task and escalates gently when you drift.

Accessibility-first macOS computer-use MCP server and CLI, with optional Jev guards on targets and inputs before irreversible actions.

Self-hostable harness to run coding agents from your phone; a mobile testing script can use Jev to pick the next UI interaction.

Rust MCP server for background computer use; plain-English recipe steps are placed by one Jev or Clef choice over interactive elements.

Computer-use MCP server for macOS and Windows that reads the UI tree and uses Jev to find elements, check screens and wait for states.