DEDUPED Hot AI repos, turned into use cases Get 5 a day

What you can do with Long Horizon Harness

LongHorizon-Harness is a loop that runs existing AI agents such as Claude Code, Codex, and OpenCode on desktop apps and the terminal for long tasks, checking results and saving verified progress along the way.

Trended earlier

AMAP-ML/LongHorizon-Harness on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

3 use cases

  • Run a long desktop task from the browser

    Start a multi-step computer task in a web dashboard and keep it running with checkpoints.

    View prompt
    Use the LongHorizon-Harness repo at <repo path>. Start the Dashboard with lh-harness web, create a task for <goal>, and let it run until it reports completion. Expected output: the final reply and the verified state for <goal>. Verify that every round the Auditor accepted is listed as a checkpoint before you report success.

  • Delegate a terminal task to a chosen agent

    Send a command-line job to a specific agent backend and collect normalized results.

    View prompt
    Use the LongHorizon-Harness repo at <repo path> to run a terminal task for <goal> with the --agent opencode option. Expected output: the normalized result file or summary for <goal>. Verify that the tests or commands named in the goal were actually executed and passed.

  • Split planning, execution, and auditing across models

    Assign a different model or backend to the Manager, Executor, and Auditor of one task.

    View prompt
    Use the LongHorizon-Harness repo at <repo path> to run a task for <goal> with a different model assigned to the Manager, Executor, and Auditor. Expected output: a verified result and a list of accepted checkpoints. Verify that the Auditor inspected the real files or logs rather than relying on the Executor's claim.

How to use Long Horizon Harness

  1. Check you have what it needs: uv, or pip with Python 3.10 or later; One agent runtime on PATH, such as codex, claude, or opencode; A goal for the agent and a project folder to work in.
  2. Open AMAP-ML/LongHorizon-Harness on GitHub and read the README and license.
  3. Complete the Installation steps in the README: install the harness and make sure one agent runtime is on PATH.
  4. Run lh-harness web to start the Dashboard.
  5. In the browser, start a new task, describe the goal, and choose a backend and model for the Manager, Executor, and Auditor.
  6. Answer any approval requests and send extra instructions mid-run if the task needs changes.

These steps come from our top use case, Run a long desktop task from the browser, which also has a copy-paste agent prompt.

Long Horizon Harness alternatives · Best AI repos for Work and operations

About this repo

Requirements

  • uv, or pip with Python 3.10 or later
  • One agent runtime on PATH, such as codex, claude, or opencode
  • A goal for the agent and a project folder to work in
Maintain Long Horizon Harness? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/amap-ml-longhorizon-harness.svg)](https://dedupedai.com/use-cases/amap-ml-longhorizon-harness/?ref=badge)

More badge styles and HTML

Questions about Long Horizon Harness

What is Long Horizon Harness?

LongHorizon-Harness is a loop that runs existing AI agents such as Claude Code, Codex, and OpenCode on desktop apps and the terminal for long tasks, checking results and saving verified progress along the way. It is an open-source project on GitHub: https://github.com/AMAP-ML/LongHorizon-Harness.

Who is Long Horizon Harness for?

Developers and operators who already use a coding or computer-use agent and need a multi-hour task to keep making verified progress without restarting from scratch.

What can I do with Long Horizon Harness?

3 use cases so far, for example: Run a long desktop task from the browser; Delegate a terminal task to a chosen agent; Split planning, execution, and auditing across models. Each has steps and a copy-paste agent prompt.

What do I need to run Long Horizon Harness?

uv, or pip with Python 3.10 or later; One agent runtime on PATH, such as codex, claude, or opencode; A goal for the agent and a project folder to work in.

What are alternatives to Long Horizon Harness?

Other hot AI repos in Work and operations: AI Job Search, Solidcraft, Fastbrowse, Awesome AI Agent Platforms, Nautilo.

Is Long Horizon Harness safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.