memory-recall
GitHub通过MemSearch搜索并召回过往会话记忆、调试笔记及项目知识。支持查询、获取详情及还原原始对话,适用于上下文包含记忆提示的场景,帮助恢复历史决策与知识。
触发场景
安装
npx skills add zilliztech/memsearch --skill memory-recall -g -y
SKILL.md
Frontmatter
{
"name": "memory-recall",
"description": "Search and recall relevant memories from past sessions via MemSearch. Use for past decisions, debugging notes, previous conversations, and project knowledge, especially when the context includes a MemSearch memory hint. Skip purely current-code questions or when the user asks to ignore memory."
}
Search memories relevant to the user's current question. The plugin's tools resolve the requesting session's checkout and configured collection, and recover pending capture before recall.
Steps
-
Use
memory_searchwith a concrete query andtop_k: 5. It returns text containing a JSON array of objects withchunk_hash,contentandsource. When calling throughexecute, return the search result and inspect its text before selecting hashes. Evaluate relevance before expanding results. -
Use
memory_getwith the most promisingchunk_hashvalues to read full Markdown sections. -
For claims requiring original dialogue, use
memory_transcriptwithsession_id,turn_idanddb_pathfrom the expandedsession:/turn:/db:anchor. Setcontext: 3; for an anchor without a turn, uselimit: 10.- If OpenCode transcript lookup fails after an upgrade, distinguish an incompatible host/plugin pair, an unavailable database or session/turn, and an incomplete V1-to-V2 database migration. See OpenCode diagnostics, also used by
memory-config. Check the referenced conversation only; a lookup failure does not justify scanning unrelated transcripts. - Keep existing markdown and
session:/turn:/db:anchors unchanged. Return useful search/expand results with the L3 limitation stated. If host migration is needed, direct the user to OpenCode's migration guidance; do not migrate the database or rewrite anchors during recall. Do not describe a summary as verified original dialogue.
- If OpenCode transcript lookup fails after an upgrade, distinguish an incompatible host/plugin pair, an unavailable database or session/turn, and an incomplete V1-to-V2 database migration. See OpenCode diagnostics, also used by
-
Return a concise account of relevant facts with dates and source files. Distinguish journal summaries from verified dialogue. If nothing relevant is found, say so.
If the query is unclear, inspect recent daily Markdown files under .memsearch/memory/ to identify a topic, then search. Avoid unrelated memory and transcript scans. A capture-pending diagnostic means new memories may still be recovering; existing Markdown/search results remain useful.
These tools require OpenCode V2. V1 users pin the published @zilliz/memsearch-opencode@0.3.17. Plugin 0.4.0 supports OpenCode >=2.0.32 <3. OpenCode's own database migration remains user-owned.
版本历史
-
65d8b22
当前 2026-11-02 22:12
支持OpenCode V2,发布插件0.4.0,新增有限捕获、持久恢复和无状态原生摘要功能,优化作用域召回工具。
-
4ad9ee4
2026-09-09 04:50
修复配置问题,确保目录派生的集成集合仅作为回退默认值,允许显式项目和全局设置覆盖。
- 8cec40e 2026-07-24 20:49


