AI Open-Source Efficiency Guide

Aug 24, 2026 · Artificial Intelligence

LongHorizon-Harness: A Three-Role Loop That Keeps AI Agents Alive on Long Tasks

Amap's open-source LongHorizon-Harness wraps existing agents (Claude Code, Codex, OpenCode, DeepSeek Harness) in a Manager-Executor-Auditor loop, raising WeaveBench pass rate from 51.8% to 80.7%, tripling OSWorld 2.0 desktop task completion, and cutting Terminal-Bench 2.1 token use by 24% — all without changing the underlying models.