Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

How memory search works v1.0.0

Use this resource to design or debug search over the memory graph

New

  • 311 downloads
  • 150 likes
  • 111 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install memory-search-internals

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent follows each search step in the knowledge graph: query parsing, execution, normalization, deduplication above 85% similarity, cross-reference boosting and final ranking. It helps find out why a relevant entry was not returned.

Mostly picked by

Updated November 2, 2026

Card for the “How memory search works” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: search steps, deduplication and result format
  • references/: entity extraction and query merging
  • rules/: graph consistency and stale node detection

Good fit for

  • Memory search misses relevant entries
  • You are designing how memory results are ranked

Not for

    Tags

    • memory
    • graph
    • search

    About

    You say

    “Why doesn't the search return this entity? Trace the steps of the query.”

    Card for the “How memory search works” skill

    Skill published by yonatangross under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to design or debug search over the memory graph
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/entity-extraction.md2.8 KB
    • references/query-merging.md2.3 KB
    • rules/_sections.md0.7 KB
    • rules/graph-consistency.md3.5 KB
    • rules/stale-node-detection.md3.3 KB
    • SKILL.md8.3 KB
    • test-cases.json2.2 KB

    Origin and licence

    Listed unmodified

    Author
    yonatangross
    Source
    github.com/yonatangross/orchestkit/tree/18a6aaa53d9971ef094b0758b08dfc606a1ea4bc/src/skills/memory-fabric
    Licence
    MIT

    Notice

    « memory-fabric » (yonatangross, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.