🧠 MemoryAPI

Persistent memory for AI agents and LLMs — REST API + MCP native

MemoryAPI gives your AI agent a persistent, searchable memory across sessions. Store memories in natural language, retrieve them semantically — no exact keywords needed.

🌐 memoryapi.org | 📡 API: api.memoryapi.org

Features

• 🧠 Semantic Search — find memories by meaning, not keywords

• 🔌 MCP Native — plug into Claude, Cursor, Windsurf instantly

• ⚡ REST API — simple HTTP endpoints, any language

• 🔑 API Key Auth — secure, namespaced per agent

• 📊 Usage Tracking — memory count and plan limits

• 🌍 Always On — hosted at api.memoryapi.org

Related MCP server: aimemory

Quick Start

1. Get an API Key

curl -X POST https://api.memoryapi.org/keys \
  -H "Content-Type: application/json" \
  -d '{"agent_id": "my-agent", "email": "you@example.com"}'

Returns:

{
  "api_key": "mem_xxxxxxxx.yyyyyyyy",
  "message": "Save this key securely — it will not be shown again."
}

2. Store a Memory

curl -X POST https://api.memoryapi.org/memory \
  -H "Content-Type: application/json" \
  -H "x-api-key: mem_xxxxxxxx.yyyyyyyy" \
  -d '{"content": "User prefers dark mode and React Native"}'

3. Search Memories

curl "https://api.memoryapi.org/memory?query=what+does+the+user+prefer" \
  -H "x-api-key: mem_xxxxxxxx.yyyyyyyy"

MCP Integration

Add to your MCP client config (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "memoryapi": {
      "url": "https://api.memoryapi.org/mcp",
      "headers": {
        "x-api-key": "mem_xxxxxxxx.yyyyyyyy"
      }
    }
  }
}

Available MCP Tools

REST API Reference

POST /memory

Store a memory.

Headers: x-api-key: your-key

Body:

{
  "content": "string (required, max 10,000 chars)",
  "metadata": { "type": "preference" }
}

GET /memory?query=...

Semantic search across memories.

Headers: x-api-key: your-key

Query params:

• query (required) — natural language search

• limit (optional, default 10) — max results

• threshold (optional, default 0.4) — similarity threshold

GET /memory/list

List all memories for the agent.

Query params:

• limit (default 50)

• offset (default 0)

DELETE /memory/:id

Delete a specific memory.

POST /keys

Generate a new API key.

Body:

{
  "agent_id": "my-agent",
  "email": "you@example.com",
  "plan": "free"
}

Pricing

Tech Stack

• Runtime: Node.js + Express

• Database: Supabase (PostgreSQL + pgvector)

• Embeddings: OpenAI text-embedding-3-small

• Auth: bcrypt-hashed API keys

• Protocol: MCP 2024-11-05

License

MIT © 2026 Ocean Digital Group