Saltar al contenido
TakoAPI
Volver a skills

agentmemory

por badaramoni

DevOps & Cloud
2.6kDescargas según clawskills.sh
4Estrellas
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

End-to-end encrypted cloud memory for AI agents.

Descripción

Qué hace esta skill

AgentMemory is a cloud storage service for AI agents with end-to-end encryption, semantic search, and 100GB free storage. It stores memories, files, and secrets, syncing automatically across sessions and devices.

Local memory files lose context on restart, can't be searched semantically, and store secrets in plain text; AgentMemory replaces all three with persistent cloud storage, vector search, and an encrypted secrets vault.

Cuándo usarla

  • Persisting user preferences between agent sessions
  • Storing API keys and credentials in an encrypted vault
  • Searching past context by meaning instead of exact keywords
  • Uploading documents and images for agents to reference later
  • Syncing agent memory across multiple devices or restarts

Flujo de trabajo de ejemplo

ENTRADA

User asks: Remember that I prefer TypeScript for all new projects

AGENTE
  1. 1

    Search /api/memories/search to check for an existing TypeScript preference memory

  2. 2

    Find no duplicate, POST new memory to /api/memories with content and metadata category 'preferences'

  3. 3

    Receive confirmation response with memory ID

  4. 4

    Auto-sync propagates the memory to cloud for retrieval in future sessions

SALIDA

Memory stored with ID mem_abc123; future sessions retrieve the TypeScript preference via semantic search

Requisitos

  • AgentMemory account at agentmemory.cloud
  • AgentMemory API key (am_xxx format, obtained after account creation)

Instalación

clawhub install badaramoni/agentmemory

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

Enlaces