啊啊啊,每换一个 AI 编程工具,都得把项目背景从头讲一遍?🥲 腾讯混元刚开源的 MemHub,能把 Claude Code、Cursor、Codex 里的对话记录汇成一份记忆,存在你电脑上。这几个工具里的 AI 都能自己去翻这份记忆,不用你从头讲了! 提取记忆要调用自己配的模型,介意对话记录发给模型厂商的话,建议可以用本机 Ollama~
tencent just open-sourced a 30b model (~3b active) built for one job: deciding what an ai agent should remember. dropped into four memory frameworks, tencent's own tests have it edging claude opus 5…
Stop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your AI harness that connects across your different tools (Cursor, Claude Code, Codex). It keeps your proprietary data completely local, and it actually learns over time.
A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.