본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

agent-memory

dennis-da-menace 제작

AI & LLMs
13.3kclawskills.sh가 보고한 다운로드 수
14스타
20조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Persistent memory system for AI agents.

설명

이 스킬이 하는 일

Persistent memory layer for AI agents using a local SQLite database. Stores facts, experience-based lessons, and named entities across sessions. Provides structured recall by tag, context, or search query.

Unlike in-context memory that resets each session, this persists structured facts and lessons to disk and makes them searchable by tag or context.

사용 시점

  • Resuming an agent session with full context from previous runs
  • Recording lessons after a failed automation to avoid repeating mistakes
  • Tracking team members and their roles across multiple projects
  • Storing API quirks or domain facts discovered during a task
  • Loading relevant background before starting a new conversation

예시 워크플로

입력

User asks: 'Remember that the staging API requires a special header, and log that we learned this the hard way'

에이전트
  1. 1

    Call mem.remember() with the API header fact and a tag like 'staging-api'

  2. 2

    Call mem.learn() with action='used staging API without header', outcome='negative', insight='staging API requires X-Custom-Header'

  3. 3

    On next session start, call mem.recall('staging API') to surface the stored fact

  4. 4

    Call mem.get_lessons(context='staging-api') to retrieve the recorded lesson

출력

Agent starts future sessions aware of the staging API requirement without being told again

설치

clawhub install dennis-da-menace/agent-memory

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

링크