AMAP-ML/LongHorizon-Harness
1,410 stars · Last commit 2026-08-20
The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.
README preview
<div align="center"> # LongHorizon-Harness ### Loop Engineering for Computer-Use Agents **Give Claude Code, Codex, OpenCode, or DeepSeek Harness a goal once. Keep it working across desktop apps and the terminal for dozens of hours.** **Plan → act → verify → checkpoint or recover → repeat — until the work is actually done.** <p align="center"> <a href="https://lh-harness.pages.dev"><img src="https://img.shields.io/badge/🌐-Website-1f6feb.svg?style=flat-square" alt="Website" /></a> <a href="https://arxiv.org/abs/2608.01964"><img src="https://img.shields.io/badge/arXiv-2608.01964-b31b1b.svg?style=flat-square" alt="arXiv 2608.01964" /></a> <a href="https://github.com/AMAP-ML/LongHorizon-Harness"><img src="https://img.shields.io/badge/GitHub-Repository-181717.svg?style=flat-square&logo=github&logoColor=white" alt="GitHub repository" /></a> <img src="https://img.shields.io/badge/🤗-Trajectory_Coming_Soon-ffce00.svg?style=flat-square" alt="Hugging Face trajectory" /> <a href="https://huggingface.co/papers/2608.01964"><img src="https://img.shields.io/badge/🤗_Daily_Papers-2608.01964-ff8800.svg?style=flat-square" alt="Hugging Face Daily Papers" /></a> <a href="./LICENSE"><img src="https://img.shields.io/badge/License-MIT-2ea44f.svg?style=flat-square" alt="MIT License" /></a> </p> [](https://www.python.org/)