engramclaw
Sistema de memoria persistente para agentes IA. Usa mem_save después de bugfixes, decisiones, descubrimientos, cambios de config. Usa mem_search cuando el usuario menciona "remember"/"recordar" o al empezar trabajo que se solapa con sesiones previas. Usa mem_session_summary antes de terminar sesiones para preservar contexto.
Best for AI agents needing persisten…Works with GitHubLow risk
⌘source
- author
@LeoYeAI- language
- Python
★2kstars
306forks
May 6, 2026
✦overview.md
Key Features
- ·Save memories after bugfixes, decisions, discoveries
- ·Search memories on user request or session overlap
- ·Sumarize sessions before ending to preserve context
Use Cases
- →An AI agent saves a discovered configuration fix for reuse in future sessions.
- →A user asks 'remember my preference' and the agent retrieves the stored memory.
- →Before ending a session, the agent automatically summarizes key decisions to maintain continuity.
Best for
- ✓AI agents needing persistent context
- ✓multi-session workflows
- ✓developer assistants
Not ideal for
- !one-off tasks
- !projects with no session overlap
FAQs
name
engram
description
Sistema de memoria persistente para agentes IA. Usa mem_save después de bugfixes, decisiones, descubrimientos, cambios de config. Usa mem_search cuando el usuario menciona "remember"/"recordar" o al empezar trabajo que se solapa con sesiones previas. Usa mem_session_summary antes de terminar sesiones para preservar contexto.
homepage:https://github.com/Gentleman-Programming/engram
metadata:{"openclaw":{"emoji":"🧠","requires":{"bins":["mcporter","engram"],"env":[]},"platforms":["macOS","Linux","Windows"],"install":[{"id":"mcporter-npm","kind":"npm","package":"mcporter","bins":["mcporter"],"label":"Install MCPorter via npm (all platforms)","platforms":["macOS","Linux","Windows"]},{"id":"mcporter-brew","kind":"brew","formula":"steipete/tap/mcporter","bins":["mcporter"],"label":"Install MCPorter via Homebrew (macOS/Linux)","platforms":["macOS","Linux"]},{"id":"engram-brew","kind":"brew","formula":"gentleman-programming/tap/engram","bins":["engram"],"label":"Install Engram via Homebrew (macOS/Linux)","platforms":["macOS","Linux"]},{"id":"engram-binary","kind":"manual","label":"Download Engram binary from GitHub Releases","url":"https://github.com/Gentleman-Programming/engram/releases","platforms":["macOS","Linux","Windows"]}]}}
Engram - Memoria Persistente para Agentes IA
Engram te da memoria persistente entre sesiones. Recuerdas bugfixes, decisiones de arquitectura, patrones y descubrimientos de conversaciones previas.
⚠️ IMPORTANTE: Mecanismo de Activación
NO es automático como cron job → Requiere decisión ACTIVA del agente.
✅ Cuándo el agente LLAMA a Engram:
| Momento | Herramienta | Razón |
|---|---|---|
| INICIO de sesión | mem_context | Recuperar trabajo previo |
| Después de trabajo significativo | mem_save | Guardar descubrimientos |
| Usuario dice "recuerda"/"recordar" | mem_search | Buscar en memoria |
| Empezando trabajo similar | mem_search | Verificar si ya se hizo |
| FIN de sesión | mem_session_summary | Preservar contexto |
| Después de compactación de contexto | mem_context | Recuperar estado |
❌ Cuándo el agente NO llama a Engram:
- Cada mensaje del usuario (ruido)
- Heartbeats (gasta tokens innecesariamente)
- Crons en background (no es el propósito)
- Tool calls triviales (no vale la pena guardarlo)
🤖 Decisión del Agente:
El agente evalúa el contexto y decide:
$install
1-click copynpx skills add LeoYeAI/openclaw-master-skills --skill engramclawSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
3/ 5
goodMostly clear, but there are still a few confusing or poorly structured parts.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.