Pular para o conteúdo
TakoAPI
Voltar às skills

aister-vector-memory

por alekhm

Search & Research
635Downloads informados pelo clawskills.sh
1Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

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

Descrição

O que esta skill faz

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.

Quando usá-la

  • 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

Exemplo de fluxo de trabalho

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

SAÍDA

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

Instalação

clawhub install alekhm/aister-vector-memory

Execute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.

Links