Phone Harness

macOS Harness is an experimental, MIT-licensed, macOS-only Python harness from browser-use that gives an LLM or coding agent raw primitives for controlling a Mac in one persistent Python process, without app-specific tools, recipes, or framework rails. Its six core primitives—`see`, `key`, `type`, `click`, `ax`, and `script`—capture native and Electron app windows, send keyboard and coordinate input directly to an application process, expose Apple Accessibility and Apple Events, execute AppleScript, and draw a click-through pointer without moving the physical cursor. The agent can write missing task logic in ordinary Python during execution. The same process provides access to a real, logged-in Chrome browser through Browser Harness, as well as the local filesystem and shell commands through Python, `Path`, and `subprocess`. It can capture background application windows without bringing them to the foreground and does not activate or raise the target app. The project includes installation and skill-registration workflows, a `doctor` command for checking required macOS permissions, and verification instructions. Anonymous telemetry is enabled by default and records the CLI command category, success, duration, package version, operating system and architecture, and detected agent client; the project states that it does not record prompts, app names, screenshots, UI text, scripts, paths, or window titles, and provides `macos-harness telemetry disable` to turn telemetry off.

Better Harness is an open-source Harness Engineering platform for coding agents. It analyzes project and, where supported, session evidence around an agent's work rather than only its final code diff, evaluating the Agent Work Loop for issues such as task understanding, validation, delivery control, and retained lessons. It turns supported gaps into prioritized findings linked to their evidence, expected outcomes, repair boundaries, and acceptance checks, and produces host-specific reports in formats including HTML, paired Markdown, or native Canvas reports. The platform also supports defining harnesses as code, running controlled experiments, inspecting evidence, and comparing outcomes across coding-agent hosts such as Claude Code, Codex, Qoder, Cursor, and GitHub Copilot CLI.

Codex iOS Assistant is an open-source system for controlling and inspecting an iPhone from Codex running on a Mac. Its `iphone` CLI sends private commands through iMessage to an iOS Shortcut; the Shortcut performs native iOS actions and returns device context through an authenticated HTTPS response routed via Cloudflare Tunnel to a receiver on the Mac. A per-user macOS LaunchAgent runs the Messages sender outside the Codex sandbox over a Unix socket. The system can read visible screen text, save screenshots, access or replace the clipboard, manage alarms, open specified apps, control timers, the flashlight, and Low Power Mode, place calls, and read Mac Contacts and the Mac Messages database. Message composition creates a draft for review; the CLI does not send ordinary messages, make purchases, install apps, order food, or request rides. It requires macOS 14 or newer, Python 3.11 or newer, Messages, Xcode Command Line Tools, an iPhone reachable at a configured iMessage address, iCloud sync for Shortcuts, and a Cloudflare-managed domain. Installation uses the repository scripts and creates an iOS Shortcut containing 95 native Shortcuts actions, with a manually configured iPhone message automation.

Port22 is a tool for remotely running and controlling code-focused AI agents. It uses a Mac agent paired with a phone to drive agents such as Claude Code, Codex, OpenCode, and Aider, providing live transcripts, in-phone approval, LAN support, and an end-to-end encrypted relay.