# 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.

## Install

Copy the content below into your project:

## Quick Use

```bash
# Run Recall MCP from npx (no install)
npx -y @joseairosa/recall

# Or install globally
npm install -g @joseairosa/recall
```

```bash
# One-liner: install the Claude Code plugin
curl -fsSL https://raw.githubusercontent.com/joseairosa/recall/main/scripts/install-plugin.sh | bash
```

## Intro

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](https://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) |

```json
{
  "mcpServers": {
    "recall": {
      "url": "https://recallmcp.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}
```

→ **[Get started at recallmcp.com](https://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).

## Source & Thanks

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

---

<!-- ZH -->

## 快速使用

```bash
# 用 npx 直接运行（无需安装）
npx -y @joseairosa/recall

# 或全局安装
npm install -g @joseairosa/recall
```

```bash
# 一键安装 Claude Code 插件
curl -fsSL https://raw.githubusercontent.com/joseairosa/recall/main/scripts/install-plugin.sh | bash
```

## 简介

Recall 是一个基于 MCP 的记忆层：把决策、需求、代码模式等跨会话保存下来，减少 Claude/Agent 每次从零开始。它支持 Redis/Valkey 自托管或托管服务，并在 README 里明确了记忆数据的安全边界。

**最适合：** 需要跨多次会话保留“项目决策/规范/需求”的 Agent 工作流

**适配：** Claude Code/Claude Desktop、Node.js 18+、Redis/Valkey（可选）、通过 MCP 客户端接入

**配置时间：** 2–10 分钟

### 关键事实（已验证）

- README 列出托管服务定价（Free 500 memories；Pro 5K；Team 25K）。
- README 写明自托管需要 Redis ≥6 或 Valkey，以及 Node.js ≥18。
- GitHub：167 stars · 18 forks；最近更新 2026-04-09（GitHub API 验证）。

## 正文

把 Recall 当成基础设施来接入：先决定记忆数据是落在自有 Redis/Valkey 还是托管实例，然后把 MCP 命令接到你的 Agent 客户端配置里。团队使用时把记忆当作敏感数据，按 README 的建议做访问控制与加密。

上线时先从少量结构化类型（directive/decision/requirement）开始，再逐步扩展。

### README 原文节选（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](https://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) |

```json
{
  "mcpServers": {
    "recall": {
      "url": "https://recallmcp.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}
```

→ **[Get started at recallmcp.com](https://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

**一定要 Redis 吗？**
答：不一定。README 表格写明托管模式不需要 Redis；自托管则用 Redis/Valkey。

**能不能快速开始？**
答：README 提到托管模式用一段配置可在约 2 分钟上线。

**最大的风险是什么？**
答：记忆可能包含敏感信息；按 README 建议为 Redis/Valkey 配置鉴权、TLS 与网络隔离。

## 来源与感谢

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


---
Source: https://tokrepo.com/en/workflows/recall-persistent-memory-mcp-for-claude-agents
Author: MCP Hub