AMAP-ML/LongHorizon-Harness helps remove repetitive manual operations from a workflow

说明与用途

**简短介绍**

AMAP-ML/LongHorizon-Harness是一款开源项目，旨在长期运行 AI 代理，跨越桌面应用和 CLI，保留任务状态并确保复杂工作流程的可靠进展。它提供了新上下文执行、可靠的状态、独立审计、可恢复的进度和原生 Claude Code / Codex / OpenClaw 集成等功能。

**价值**

AMAP-ML/LongHorizon-Harness的主要价值在于帮助用户移除工作流程中的重复手动操作。

**典型接入方式**

AMAP-ML/LongHorizon-Harness可以通过以下方式接入：

• 直接使用 CLI
• 使用 API 或 SDK
• 将其集成到其他工具中，以创建可重复的流程

**生产可用性**

AMAP-ML/LongHorizon-Harness有很高的生产可用性，其最近的活跃度、采用率和生态系统信号表明它已经准备好用于严肃的试验。

问题

AMAP-ML/LongHorizon-Harness helps remove repetitive manual operations from a workflow.

结果

High for an OSS candidate: recent activity, adoption, and ecosystem signals are strong enough for a serious pilot.

工作流

• remove manual work
• connect tools into repeatable flows
• schedule operational tasks

证据

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.

来源