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.

Vector similarity search v1.0.0

Use this resource to find semantically close items in a corpus

New

  • 510 downloads
  • 230 likes
  • 152 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install vector-similarity-search-2

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 chooses between two paths: HNSW search over a large corpus, optionally quantized to reduce memory, and the WASM router for a small set of hot patterns. It tunes search parameters and can use hyperbolic embeddings. You get the closest matches.

Mostly picked by

Updated November 2, 2026

Card for the “Vector similarity search” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: standard and quantized search
  • SKILL.md: tuning, WASM pattern router and performance comparison

Good fit for

  • You look for similar documents in a large corpus
  • You route queries to about ten fixed patterns

Not for

    Tags

    • vectors
    • hnsw
    • similarity
    • embeddings

    About

    You say

    “Find the ten documents closest to this brief in our ticket corpus.”

    Card for the “Vector similarity search” skill

    Skill published by ruvnet 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 find semantically close items in a corpus
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md6.1 KB

    Origin and licence

    Listed unmodified

    Author
    ruvnet
    Source
    github.com/ruvnet/ruflo/tree/89b0cd02dd99ea1f63437fde6c05992ec53cc22b/plugins/ruflo-agentdb/skills/vector-search
    Licence
    MIT

    Notice

    « vector-search » (ruvnet, 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.