MemoryAPI
Persistent memory for AI agents. Store and semantically search memories via REST API or MCP. Free tier available.
README
š§ MemoryAPI
Persistent memory for AI agents and LLMs ā REST API + MCP native
MemoryAPI gives your AI agent a persistent, searchable memory across sessions. Store memories in natural language, retrieve them semantically ā no exact keywords needed.
š memoryapi.org | š” API: api.memoryapi.org
Features
- š§ Semantic Search ā find memories by meaning, not keywords
- š MCP Native ā plug into Claude, Cursor, Windsurf instantly
- ā” REST API ā simple HTTP endpoints, any language
- š API Key Auth ā secure, namespaced per agent
- š Usage Tracking ā memory count and plan limits
- š Always On ā hosted at api.memoryapi.org
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 ā 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
| Tool | Description |
|---|---|
store_memory |
Store a memory in natural language |
search_memory |
Semantically search memories |
list_memories |
List all stored memories |
delete_memory |
Delete a memory by ID |
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) ā natural language searchlimit(optional, default 10) ā max resultsthreshold(optional, default 0.4) ā 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
| Plan | Price | Memories | Agents |
|---|---|---|---|
| Free | $0/mo | 100 | 1 |
| Starter | $19/mo | 10,000 | 5 |
| Pro | $49/mo | Unlimited | Unlimited |
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 Ā© 2026 Ocean Digital Group
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.