본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

simplemem

nantes 제작

Search & Research
383clawskills.sh가 보고한 다운로드 수
2스타
0조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Efficient Lifelong Memory for LLM Agents - semantic compression, cross-session memory, and intent-aware retrieval.

설명

이 스킬이 하는 일

SimpleMem gives LLM agents persistent memory across sessions by compressing interactions into compact units and retrieving them based on intent. It uses a multi-index approach combining semantic, lexical, and symbolic layers. Without an OpenAI key, it falls back to JSON-based keyword search.

Unlike naive context stuffing, SimpleMem compresses and indexes memories so retrieval stays fast and relevant even as history grows.

사용 시점

  • Remembering user preferences across chat sessions
  • Storing project context for long-running agent tasks
  • Reducing repeated context in multi-turn conversations
  • Retrieving relevant past interactions during planning
  • Compressing conversation history to stay within token limits

예시 워크플로

입력

User asks: Remember that I prefer dark mode and always use TypeScript

에이전트
  1. 1

    Calls simplemem add with the preference string and a user ID

  2. 2

    SimpleMem compresses and stores the memory unit in persistent storage

  3. 3

    In a later session, agent calls simplemem retrieve with query about user preferences

  4. 4

    SimpleMem runs intent-aware search across semantic and lexical indexes

  5. 5

    Returns ranked memory results with the stored preference

출력

Agent recalls dark mode and TypeScript preference without re-prompting the user

요구 사항

  • OPENAI_API_KEY environment variable (optional, required for semantic embeddings)

설치

clawhub install nantes/simplemem

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

링크