Saltar al contenido
TakoAPI
Volver a skills

brain-cms

por harrey401

Coding Agents & IDEs
339Descargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Continuum Memory System (CMS) for OpenClaw agents.

Descripción

Qué hace esta skill

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%.

Cuándo usarla

  • 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

Flujo de trabajo de ejemplo

ENTRADA

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

AGENTE
  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

SALIDA

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

Requisitos

  • Ollama installed and running locally

Instalación

clawhub install harrey401/brain-cms

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces