Dev Radar
Support
LiveUpdated 2026-09-23 16:31 UTC

AI Agent 跑完任务后,最麻烦的往往不是结果,而是过程没法回头看。

AI Agent 跑完任务后,最麻烦的往往不是结果,而是过程没法回头看。 Shepherd 想做的,就是给 Agent 的执行过程加一层类似 Git 的“版本控制”。…

This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.

AI Agent 跑完任务后,最麻烦的往往不是结果,而是过程没法回头看。 Shepherd 想做的,就是给 Agent 的执行过程加一层类似 Git 的“版本控制”。 每次运行都会留下完整的执行轨迹,代码和环境改动先以提案形式保存,确认后再应用,不满意也可以直接丢弃。 更有意思的是,Agent 运行可以被观察、分叉、重放和回滚,方便重新尝试不同方案。 底层通过 Copy-on-Write 管理 Agent 和环境,官方测试中分叉速度约是 docker commit 的 5 倍,重放时 KV Cache 复用率约 95%。 目前项目还处于早期 Alpha,比较适合研究 Agent 监督、训练和工作流控制。 🔗 https://github.com/shepherd-agents/shepherd

Posted by lumxss (24.8k followers) 55 min ago · 0 likes · 156 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: shepherd.

More dev work like this

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 22.6k posts from 5k X accounts over the last 21 days, 2.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 16:31 UTC. Full method.