Esta página se muestra en inglés. Una traducción al español está en curso.
KnowledgeMay 12, 2026·4 min de lectura

Recall — Persistent Memory MCP for Claude Agents

Recall provides persistent cross-session memory for Claude agents via an MCP server backed by Redis/Valkey or managed cloud, with sharing and search.

Listo para agents

Este activo puede ser leído e instalado directamente por agents

TokRepo expone un comando CLI universal, contrato de instalación, metadata JSON, plan según adaptador y contenido raw para que los agents evalúen compatibilidad, riesgo y próximos pasos.

Needs Confirmation · 62/100Política: confirmar
Superficie agent
Cualquier agent MCP/CLI
Tipo
Memory
Instalación
Manual
Confianza
Confianza: Established
Entrada
npx -y @joseairosa/recall
Comando CLI universal
npx tokrepo install 9e80e920-7c69-5688-b456-2a7c2b6f2268
Introducción

Recall is an MCP-backed memory layer that keeps decisions, requirements, and reusable patterns across Claude sessions so your agent doesn’t forget critical context. It supports self-hosted Redis/Valkey or a managed service and documents the security boundaries for memory data.

Best for: agent workflows that need durable memory (project decisions, coding standards, requirements) across many sessions

Works with: Claude Code/Claude Desktop, Node.js 18+, Redis or Valkey (optional), MCP clients over stdio/HTTP

Setup time: 2–10 minutes

Key facts (verified)

  • README lists pricing tiers (Free 500 memories; Pro 5K; Team 25K) for the managed service.
  • README states Redis ≥6 or Valkey and Node.js ≥18 for self-hosting.
  • GitHub: 167 stars · 18 forks; pushed 2026-04-09 (GitHub API verified).

Main

Deploy Recall like infrastructure: decide whether memory data lives in your own Redis/Valkey or a managed instance, then wire the MCP command into your agent client config. For teams, treat memory as sensitive data and follow the README guidance on access control and TLS.

When onboarding, start with a small memory schema (directives/decisions/requirements) and only then expand to more granular memory types.

README excerpt (verbatim)

Recall 🧠

Persistent cross-session memory for Claude and other AI agents. Survives context limits, session restarts, and compaction.

Store decisions, patterns, and knowledge once — retrieve them automatically across every future conversation. No more repeating yourself. No more losing critical context when the window fills up.


Cloud vs. Self-Hosted

Recall comes in two flavours. Choose the one that fits your situation:

☁️ recallmcp.com — Managed SaaS (Recommended for most users)

Zero infrastructure. Sign up, get an API key, add one config block, done.

What you get Detail
No Redis required Fully managed storage — nothing to install or maintain
Up in 2 minutes One config block in Claude Desktop or Claude Code
Team sharing One Claude learns something, all others know instantly
Enterprise security AES-256-GCM encryption at rest, per-tenant key isolation
Auto-consolidation Automatically clusters and merges similar memories
Cross-session workflows Named threads that span multiple sessions
7 embedding providers Voyage AI, Cohere, OpenAI, Deepseek, Grok, Anthropic, Ollama
Pricing Free (500 memories) · Pro $4.99/mo (5K) · Team $9.99/mo (25K)
{
  "mcpServers": {
    "recall": {
      "url": "https://recallmcp.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Get started at recallmcp.com


🖥️ This Repository — Self-Hosted (Redis or Valkey)

Run Recall entirely on your own infrastructure. Your data never leaves your servers.

What you get Detail
Full data ownership Memories stored in your own Redis or Valkey instance
No usage limits No memory caps, no subscription required
Air-gapped deployments Works fully offline, no external API calls for storage
Bring your own embeddings Configure any of 7 providers, or use the Anthropic keyword fallback
Open source MIT licensed, fully auditable, fork-friendly
Requires Redis ≥ 6 or Valkey, Node.js ≥ 18, your own server/VPS

Best for: developers who need full control, on-premise requirements, or who already run Redis infrastructure.


⚠️ Security & Privacy Disclaimer

IMPORTANT: READ BEFORE USE

Recall stores conversation memories in either Redis or Valkey, which may contain sensitive information including:

  • Code snippets, API keys, credentials, and secrets discussed in conversations

FAQ

Q: Do I need Redis? A: No for managed mode—README says no Redis required for the cloud service; self-host uses Redis/Valkey.

Q: Is there a fast start path? A: README claims you can be up in ~2 minutes with one config block for the managed service.

Q: What’s the biggest risk? A: Memory can contain sensitive data; follow README security guidance for Redis/Valkey (auth, TLS, network controls).

🙏

Fuente y agradecimientos

Source: https://github.com/joseairosa/recall > License: MIT > GitHub stars: 167 · forks: 18

Discusión

Inicia sesión para unirte a la discusión.
Aún no hay comentarios. Sé el primero en compartir tus ideas.

Activos relacionados