Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

simplemem

bởi nantes

Search & Research
383Lượt tải do clawskills.sh công bố
2Sao
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

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

Mô tả

Kỹ năng này làm gì

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.

Khi nào nên dùng

  • 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

Quy trình ví dụ

ĐẦU VÀO

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

AGENT
  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

ĐẦU RA

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

Yêu cầu

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

Cài đặt

clawhub install nantes/simplemem

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

Liên kết