Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

aister-vector-memory

bởi alekhm

Search & Research
635Lượt tải do clawskills.sh công bố
1Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

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

Mô tả

Kỹ năng này làm gì

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.

Khi nào nên dùng

  • 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

Quy trình ví dụ

ĐẦU VÀO

User asks: /search_memory my communication style

AGENT
  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

ĐẦU RA

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

Yêu cầu

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

Cài đặt

clawhub install alekhm/aister-vector-memory

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết