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.

Agent memory architecture v1.0.0

Use this resource to design agent memory that retrieves the right information at the right time

New

  • 367 downloads
  • 250 likes
  • 226 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install agent-memory-architecture-3

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 designs an agent's memory from its types: working context, long-term memory in a vector store and a cognitive architecture that organizes them. It focuses on retrieval, chunking and the choice of vector store. You get a memory whose gaps are under control.

Mostly picked by

Updated November 2, 2026

Card for the “Agent memory architecture” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: capabilities, patterns and memory type architecture
  • sub-skills/: type architecture, vector store selection, chunking strategy and anti-patterns

Good fit for

  • Your agent gives inconsistent answers about facts it already knows
  • You must choose a vector store for a knowledge base

Not for

    Tags

    • memory
    • agents
    • vectors
    • retrieval

    About

    You say

    “Design our support agent's memory: session context, customer history and a procedures base.”

    Card for the “Agent memory architecture” skill

    Skill published by dokhacgiakhoa 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 agent memory that retrieves the right information at the right time
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE2.4 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md1.9 KB
    • sub-skills/chunk-without-testing-retrieval.md0 KB
    • sub-skills/chunking-strategy-pattern.md0.1 KB
    • sub-skills/memory-type-architecture.md0.1 KB
    • sub-skills/single-memory-type-for-all-data.md0.6 KB
    • sub-skills/store-everything-forever.md0 KB
    • sub-skills/vector-store-selection-pattern.md0.1 KB

    Origin and licence

    Listed unmodified

    Author
    dokhacgiakhoa
    Source
    github.com/dokhacgiakhoa/agent-skills-4-vibe-coding-cli/tree/c4a059bbf7a8d6b2162071f0fbfe74053faa6d20/.agent/skills/agent-memory-systems
    Licence
    MIT

    Notice

    « agent-memory-systems » (dokhacgiakhoa, 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.