Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

brain-cms

bởi harrey401

Coding Agents & IDEs
339Lượt tải do clawskills.sh công bố
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Continuum Memory System (CMS) for OpenClaw agents.

Mô tả

Kỹ năng này làm gì

Replaces flat MEMORY.md files with a multi-layer memory architecture for OpenClaw agents. Uses a hippocampal router, LanceDB vector store, and automated NREM/REM sleep cycles to load only relevant context per session. Modeled on neuroscience concepts like long-term potentiation and spreading activation.

Loads 50-line context cores with on-demand schema retrieval instead of injecting 150-300 lines every session, cutting token usage by 40-60%.

Khi nào nên dùng

  • Reducing token costs on long-running agents
  • Setting up persistent memory across agent sessions
  • Semantic search over accumulated agent knowledge
  • Auto-consolidating daily logs into structured schemas
  • Preserving high-significance events as permanent anchors

Quy trình ví dụ

ĐẦU VÀO

User asks: 'What happened in last week's project demo?'

AGENT
  1. 1

    Check memory/INDEX.md for relevant topic triggers

  2. 2

    Load matching semantic schema from memory/<topic>.md

  3. 3

    Query ANCHORS.md for any CRITICAL-tagged events

  4. 4

    Run vector similarity search via query_memory.py if topic is ambiguous

  5. 5

    Return consolidated context from matched layers

ĐẦU RA

Agent retrieves only the relevant episodic and anchor entries instead of loading the full memory file

Yêu cầu

  • Ollama installed and running locally

Cài đặt

clawhub install harrey401/brain-cms

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

Liên kết