memesis reindex --vec

Community

Re-embed memories efficiently after embedding model changes.

Authoremmahyde
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It enables updating all stored memory embeddings to match a new or changed embedding model, ensuring retrieval accuracy and consistency.

Core Features & Use Cases

  • Memory Re-embedding: Reads all existing memories and recalculates their embeddings using the current embedding model.
  • Atomic Table Swap: Performs an in-place update of the vector memories table to maintain database integrity.
  • Use Case: After switching to a different embedding model version, run this Skill to regenerate memory embeddings and keep retrieval relevant and precise.

Quick Start

Use the reindex --vec skill to refresh memory embeddings after changing your embedding configuration.

Dependency Matrix

Required Modules

core.embeddingscore.veccore.databasecore.models

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: memesis reindex --vec
Download link: https://github.com/emmahyde/memesis/archive/main.zip#memesis-reindex-vec

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.