Lewati ke konten
TakoAPI
Kembali ke skill

simplemem

oleh nantes

Search & Research
383Unduhan dilaporkan oleh clawskills.sh
2Bintang
0Tayangan
0 sukaMasuk untuk menyukai skill ini
—Belum ada penilaian
Penilaian Anda

Ringkasan

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

Deskripsi

Apa yang Dilakukan Skill Ini

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.

Kapan Menggunakannya

  • 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

Contoh Alur Kerja

INPUT

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

OUTPUT

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

Persyaratan

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

Instalasi

clawhub install nantes/simplemem

Jalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.

Tautan