[分享创造] 关于自己的 agent-harness 的实践与迭代过程中一些好玩的点
摘要
作者分享了自建 agent harness 的实践，思路借鉴 Codex 和 Claude Code，桌面端用 wails 写。文章讨论了 tool 的 round trip 调用与必须回传 result、agent 进程后台运行并在需要人工干预时发系统通知、四重 RAG 记忆、分层组装 prompt 和渐进式上下文压缩，以及用远程机器加固定容器唤起一次性容器执行沙箱脚本。
相关推荐
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
金融监管领域的 Harness 实践：让知识与数据驱动 Agent 稳定运行
从 Harness 到 Loop：Agent 如何走向可靠交付与持续进化？
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
ruvnet/ruflo
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated