Better Harness

Harness Engineering is Ryan Lopopolo’s anthology, field guide, and agent-context repository for improving coding-agent output without changing the underlying model or coding agent. It shapes the surrounding environment through context and tools so an agent can recover intent, operate the real system, respect authority, prove its outcome, and incorporate lessons from accepted work, corrections, failures, and user responses. The repository uses AGENTS.md to route agents to relevant arguments, cases, and proof, and provides a thesis index, playbooks, source material, and executable constraints for encoding organizational requirements and decisions. Repository-authored material is licensed under CC BY 4.0.

FrontierHarness Eval is an open evaluation benchmark and repository for measuring how coding-agent harness configurations affect software-engineering task results when the underlying model and runtime are held constant. It publishes benchmark definitions, task instructions and metadata, harness-version metadata, normalized aggregate and task-level results, and an agent-neutral workflow for evaluating additional harnesses. The benchmark runs the same model through multiple harness configurations on 30 tasks, using a frozen golden checkpoint and a fresh restore for each task. Its scripts provision the environment, run trials, record verifier-based pass/fail outcomes, measure cost, cache behavior, and speed, then normalize results and generate charts and reports. The repository also provides a CLI and skill-based workflow for evaluating a third-party harness, with infrastructure failures marked separately from task failures. The project focuses on terminal-based software-engineering tasks and states that its results may not generalize to other knowledge-work domains. The repository is published under the frontier-harness-eval organization, with isolated runtimes and checkpoint restores provided by Runta.

HarnessRouter Community Edition is the open-source edition of HarnessRouter, an agent-harness infrastructure that provides a unified Agent API to integrate language models and agent runtimes. It is maintained by HarnessRouter and is intended for deployment on users' own infrastructure to connect models such as Codex, Claude Code, and Hermes.

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.

Phone Harness is an open-source harness that lets AI agents such as Claude Code, Codex, or other LLMs control a real iPhone or Android phone without a jailbreak, injected app, Xcode, WebDriverAgent, or on-device installation. It exposes helpers for opening apps, reading screen content, tapping, scrolling, typing, and verifying actions. On iPhone, it uses the macOS iPhone Mirroring window as the transport: screenshots are captured from the window, Apple's Vision framework performs OCR and returns tap-ready coordinates, and HID-level CGEvents provide taps, long presses, drags, flicks, scrolling, Unicode typing, and shortcuts. On Android, it uses ADB over USB or Wi-Fi, combining screenshots with the phone's accessibility tree for text and element bounding boxes. Actions can be verified by capturing the screen again, with the screenshot serving as the ground truth rather than relying on a DOM. Each invocation is self-contained rather than relying on a daemon.