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.

Latent memory sharing between agents v1.0.0

Use this resource to share an orchestrator's memory with its workers without copying everything

New

  • 449 downloads
  • 193 likes
  • 250 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install latent-memory-sharing-agents

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 helps you judge whether KV-cache compaction reduces the token cost of your workers, and describes the inference changes it requires. It also covers the infrastructure prerequisites and the thresholds where the method pays off. You get a decision framework and examples.

Mostly picked by

Updated November 2, 2026

Card for the “Latent memory sharing between agents” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: concepts, inference modifications and decision framework
  • references/attention-matching-formulation.md: attention matching formulation

Good fit for

  • Your sub-agents burn too many tokens on a long history
  • You host your own models and control the KV cache

Not for

    Tags

    • memory
    • KV cache
    • orchestration
    • tokens

    About

    You say

    “My orchestrator has built up 80,000 tokens: estimate whether KV-cache compaction is worth it for my workers.”

    Card for the “Latent memory sharing between agents” skill

    Skill published by muratcankoylan 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 share an orchestrator's memory with its workers without copying everything
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/attention-matching-formulation.md3 KB
    • SKILL.md12.9 KB

    Origin and licence

    Listed unmodified

    Author
    muratcankoylan
    Source
    github.com/muratcankoylan/agent-skills-for-context-engineering/tree/9ff0c99108b36d3b886defd825d8ac1f47dba374/skills/latent-briefing
    Licence
    MIT

    Notice

    « latent-briefing » (muratcankoylan, 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.