LongHorizon-Harness

Verified state-management harness that keeps AI coding agents on long, multi-hour tasks.

Pluginfreeglobal

LongHorizon-Harness is an open-source execution and verification layer that runs on top of AI coding agents such as Claude Code and Codex. It splits long, multi-hour tasks across separate planning, execution, and auditing roles so that only independently verified progress is kept, even if the agent's context resets. It's built for developers who need an AI agent to reliably carry a complex task through to completion across both desktop and command-line workflows.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of LongHorizon-Harness - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim LongHorizon-Harness to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether LongHorizon-Harness (or something else) actually fits.

Try a problem