본문으로 건너뛰기
TakoAPI
스킬로 돌아가기
—아직 평가 없음
내 평가

요약

Local RAG system for agent memory using ChromaDB and sentence-transformers.

설명

이 스킬이 하는 일

Local RAG system that gives AI agents persistent memory across sessions. Uses ChromaDB for vector storage and sentence-transformers for local embeddings. Indexes session logs, daily notes, and markdown files for semantic search.

Runs entirely on local hardware with no external API calls, so memory stays private and works offline.

사용 시점

  • Searching past conversations before answering a question
  • Indexing daily notes so decisions persist across restarts
  • Resuming context after an agent session ends and restarts
  • Building a searchable log from agent session history
  • Scheduling automatic memory updates every few hours via cron

예시 워크플로

입력

User asks: 'What did we decide about the API design last week?'

에이전트
  1. 1

    Run recall 'API design decisions' --json to query ChromaDB

  2. 2

    Retrieve top matching chunks from indexed session digests

  3. 3

    Include relevant context in the response to the user

출력

Agent responds with relevant past decisions pulled from indexed memory files

설치

clawhub install ttboy/ouyang

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

링크