memory-search
Skill0 starsChanged 37 days agoMITView on GitHub
Searches long-term Mnemoverse memory before answering, so earlier decisions, preferences and project setup are used instead of asked again, then rates which recalled memories helped. Use when the answer may depend on an earlier session or another tool, when the user says \"like last time\", \"do you remember\", or \"check memory\", or before choosing a library, pattern or convention in a project touched before.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- krakozavr/MemContinuumtheir own version, first seen Oct 25, 2026
- troglodyte/claude-sqlite-memtheir own version, first seen Oct 15, 2026
- troglodyte/claude-neo4j-memtheir own version, first seen Oct 13, 2026
- thiagofinch/mega-braintheir own version, first seen Oct 8, 2026
- dewil/ai-toolkittheir own version, first seen Aug 25, 2026
- dewil/claude-toolkittheir own version, first seen Aug 25, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- thiagofinch/mega-brain★ 95same name
- dewil/ai-toolkit★ 9same name
- dewil/claude-toolkit★ 9same name
- krakozavr/MemContinuum★ 8same name
- Keshab0310/agent-memory★ 2same name
- jpoindexter/theft-kit★ 1same name
- troglodyte/claude-neo4j-mem★ 1same name
- troglodyte/claude-sqlite-mem★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- agent-memory-disciplineSkill
- memory-catch-upSkill
- memory-onboardSkill
- memory-saveSkill
- mnemoverse-docsSkill
- setupSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Look for the tools memory_read and memory_feedback.
- Distinctive: line 14
Search before answering when the answer could depend on something said in an earlier session or in another connected tool: a decision, a …
- Very specific: line 18
Call memory_read with the user's own words plus the project or repository name.
- Distinctive: line 19
If nothing useful comes back, try one broader query.
- Distinctive: line 26
If two memories disagree, show both with their dates and let the user decide.
- Very specific: line 27
If a memory looks wrong or out of date, say so.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Search memory before answering
Check first
Look for the tools memory_read and memory_feedback. If they are missing, memory is not connected: say so in one sentence and use the bundled setup skill if it is installed, otherwise https://mnemoverse.com/docs/api/install-by-host. Do not guess what memory would have said.
When to search
Search before answering when the answer could depend on something said in an earlier session or in another connected tool: a decision, a preference, a convention, a person, how the project is set up. General world knowledge does not need a search.
How to search
- Call
memory_readwith the user's own words plus the project or repository name. - If nothing useful comes back, try one broader query. Then stop and say what was searched, rather than looping.
- For "what changed lately" questions, use the
memory-catch-upskill.order_by: "recency"only puts the matches of this query newest first, which suits "the latest decision about X". - For a shared room (beta), pass the room's address as
domain. Rooms are separate stores, and a search without that address never covers them.
How to answer with what came back
- Say what each memory states and, when it is recorded, where it came from and when. Do not present a recalled memory as your own knowledge.
- If two memories disagree, show both with their dates and let the user decide. Do not quietly pick one.
- If a memory looks wrong or out of date, say so. It is corrected by saving a fresh statement with the
memory-saveskill, not by editing the old one.
Rate what helped
After the answer, call memory_feedback with the ids of the memories that were used: outcome 1 if a memory helped, -1 if it misled, a value between for partly. Tell it a recalled memory helped or misled, and it re-ranks what comes back next; nothing is erased by a low rating. For memories read from a shared room (beta), pass the room's address as domain. If memory_feedback has no domain parameter, or the user is a read-only member of the room, skip rating the room's memories.
Rate only memories that were actually used or actually misleading. Skip the rest.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.