تخطَّ إلى المحتوى
TakoAPI
العودة إلى المهارات

aister-vector-memory

بواسطة alekhm

Search & Research
635التنزيلات وفق ما يذكره clawskills.sh
1المشاهدات
لا إعجاباتسجّل الدخول للإعجاب بهذه المهارة
—لم يُقيَّم بعد
تقييمك

موجز

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

الوصف

ما الذي تفعله هذه المهارة

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.

متى تستخدمها

  • 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

مثال على سير العمل

الإدخال

User asks: /search_memory my communication style

الوكيل
  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

الإخراج

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

المتطلبات

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

التثبيت

clawhub install alekhm/aister-vector-memory

شغّل أمر واجهة سطر الأوامر، أو الصق النص في Claude Code أو Cursor أو Codex أو أي وكيل برمجة تستخدمه.

الروابط