by AMAP-ML · Codex Skill · ★ 1.9k
LongHorizon-Harness Advancing Long-Horizon Agents for Real-World Tasks Operate the whole computer like a human. Work across desktop apps and the command line for dozens of hours. No state drift. Verifiable progress. Complex tasks carried through to completion. [![Be
| Stars | 1,870 |
| Forks | 196 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 37.3/100 |
| Open Issues | 19 |
| Last Updated | 2026-11-11 |
| Created | 2026-08-04 |
| Platforms | claude-code, cli, codex, python |
| Est. Tokens | ~6321k |
These tools work well together with LongHorizon-Harness for enhanced workflows:
Explore other popular codex skill tools:
LongHorizon-Harness is 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-. It is categorized as a Codex Skill with 1.9k GitHub stars.
LongHorizon-Harness is primarily written in Python. It covers topics such as agent, claude, claude-code.
You can find installation instructions and usage details in the LongHorizon-Harness GitHub repository at github.com/AMAP-ML/LongHorizon-Harness. The project has 1.9k stars and 196 forks, indicating an active community.
LongHorizon-Harness is released under the MIT license, making it free to use and modify according to the license terms.