Vercel 推出 durable-harness，让 Pi、OpenCode 等智能体 harness 持久运行
Much like we did with @aisdk, we're bringing a truly open-source, runtime-agnostic solution to harness durability.
Vercel 推出开源、与运行时无关的 durable-harness，把支撑 eve 和 Workflows 的持久化基础设施扩展到 Pi、OpenCode 等所有 harness，可在本地、Vercel 或自建环境运行。智能体在失败后能自动恢复，并持续运行数小时、数天甚至数月。Guillermo Rauch 补充说，Claude Code 和 Codex 也能借此实现持久化和可观测，但它们目前并非为嵌入而设计，效率、可移植性较差，且比 Pi 或 Fx 多一层沙箱要求。
查看原帖隆重推出 𝚍𝚞𝚛𝚊𝚋𝚕𝚎-𝚑𝚊𝚛𝚗𝚎𝚜𝚜。在 Vercel 上持久运行 Pi、OpenCode、Codex、Claude Code、eve、fx 或你自己的 harness。 借助 𝚍𝚞𝚛𝚊𝚋𝚕𝚎-𝚑𝚊𝚛𝚗𝚎𝚜𝚜，智能体在失败后会自动恢复工作，并能持续运行数小时、数天乃至数月。https://t.co/XkqmULA2ng
查看原文
Introducing 𝚍𝚞𝚛𝚊𝚋𝚕𝚎-𝚑𝚊𝚛𝚗𝚎𝚜𝚜. Run Pi, OpenCode, Codex, Claude Code, eve, fx, or your own harness durably on Vercel. With 𝚍𝚞𝚛𝚊𝚋𝚕𝚎-𝚑𝚊𝚛𝚗𝚎𝚜𝚜, agents automatically resume work after failures and run for hours, days, or months. https://t.co/XkqmULA2ng
正文
Much like we did with @aisdk, we're bringing a truly open-source, runtime-agnostic solution to harness durability.
We're extending the durability infra that powers @eve and Workflows to all harnesses, like Pi and OpenCode. Local, Vercel, or DIY.
Fun fact: even Claude Code and Codex can be made durable (and observable!) this way. The catch: they're not (currently) designed for embedding, which makes them less efficient, less portable, and brings an extra sandbox requirement compared to Pi or Fx.