Saltar al contenido
TakoAPI
Volver a skills

aister-vector-memory

por alekhm

Search & Research
635Descargas según clawskills.sh
1Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Vector memory for Aister — search by meaning, not by grep!

Descripción

Qué hace esta skill

Adds semantic search to Aister's memory using PostgreSQL with pgvector and the e5-large-v2 embedding model. Queries match by meaning rather than exact keywords. Supports both English and Russian.

Finds relevant memory entries even when the query shares no words with the stored text, unlike grep or keyword search.

Cuándo usarla

  • Finding past notes when you remember the topic but not the exact wording
  • Searching stored preferences and settings by description
  • Recalling what was written about a project without knowing precise terms
  • Looking up identity or behavior notes by concept
  • Retrieving context from memory files before starting a new conversation

Flujo de trabajo de ejemplo

ENTRADA

User asks: /search_memory my communication style

AGENTE
  1. 1

    Converts the query to a 1024-dimension vector using e5-large-v2

  2. 2

    Runs cosine similarity search against stored vectors in PostgreSQL

  3. 3

    Filters results above the 0.5 similarity threshold

  4. 4

    Returns up to 5 matching memory chunks with source context

SALIDA

Excerpts from MEMORY.md or USER.md describing the user's communication preferences, ranked by semantic similarity

Requisitos

  • PostgreSQL 16 with pgvector extension (requires root or sudo to install)
  • VECTOR_MEMORY_DB_PASSWORD environment variable set to the PostgreSQL user password

Instalación

clawhub install alekhm/aister-vector-memory

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces