본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

aister-vector-memory

alekhm 제작

Search & Research
635clawskills.sh가 보고한 다운로드 수
1조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

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

설명

이 스킬이 하는 일

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.

사용 시점

  • 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

예시 워크플로

입력

User asks: /search_memory my communication style

에이전트
  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

출력

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

요구 사항

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

설치

clawhub install alekhm/aister-vector-memory

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크