返回探索

Jev 用于评估智能体运行,并接入开源自改进记忆层

帖子介绍 Jev 在智能体运行评估中的新用例,可更经济地分析 agent run 内部实际发生的情况,并提到一个开源的自改进记忆层可将该信号用于 Claude Code、Codex、Cursor 等 agent harness。

Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor -

· 2 次赞在 X 打开