Quick semantic recall — searches all memory namespaces with MMR diversity and recency weighting
复制下面这句话,粘贴给 Claude Code、Codex、Cursor 等 AI 编程工具,它会读取安装说明并在你确认后完成安装。
请阅读 https://ai.atlankj.com/install/asset/gh-ruflo-787bc418ea88 ,按照其中的说明把「recall」安装到你(当前 AI 工具)中。执行前先告诉我将运行的命令和写入的位置,等我确认。
查看 AI 将读取的安装说明正在读取 GitHub 原文…
内容来自 GitHub 原始文件,由原作者维护。在 GitHub 查看
$ARGUMENTS
Semantic recall across all memory namespaces using HNSW vector search with MMR diversity reranking.
npx @claude-flow/cli@latest memory search --query "$ARGUMENTS" --limit 5
For richer results when ruvector is available:
npx ruvector search "$ARGUMENTS" --hybrid --limit 5
This searches across patterns, tasks, solutions, feedback, security, and claude-memories namespaces. Results are ranked by composite score: cosine similarity * MMR diversity * recency decay.
If no arguments provided, show recent memory entries:
npx @claude-flow/cli@latest memory list --limit 10