LongHorizon-Harness

LongHorizon-Harness

AMAP-ML

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.

1.1k Stars
119 Forks
8 Watchers
Python Language
mit License
100 SrcLog Score
Cost to Build
$3.63M
Market Value
$17.10M

Growth over time

2 data points  ·  2026-08-14 → 2026-08-24
Stars Forks Watchers
💬

How do you feel about this project?

Ask AI about LongHorizon-Harness

Question copied to clipboard

What is the AMAP-ML/LongHorizon-Harness GitHub project? Description: "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.". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone LongHorizon-Harness

Clone via HTTPS

git clone https://github.com/AMAP-ML/LongHorizon-Harness.git

Clone via SSH

[email protected]:AMAP-ML/LongHorizon-Harness.git

Download ZIP

Download main.zip

Found an issue?

Report bugs or request features on the LongHorizon-Harness issue tracker:

Open GitHub Issues