// integration

AgentRAM + Claude Code

Claude Code speaks MCP, so wiring in AgentRAM's memory takes one command. Add the server, restart, and your agent can store and recall named memory across sessions.

In one line: Add AgentRAM's MCP server to Claude Code and your agent can store and recall persistent memory as native tools.

What you get

Persistent memory that survives across Claude Code sessions: named values you store once and recall later, shared memory for multi-agent work, and no vector database to run. Memory shows up as tools your agent calls directly. For the concepts underneath, see the MCP integration overview.

Prerequisites

Add the server

The quickest way is the Claude Code CLI. From your project directory:

claude mcp add agentram \\
  -e AGENTRAM_API_KEY=agentram_your_key_here \\
  -- npx -y agentram-mcp

Prefer to edit config directly? Add this to your Claude Code MCP configuration:

{
  "mcpServers": {
    "agentram": {
      "command": "npx",
      "args": ["-y", "agentram-mcp"],
      "env": { "AGENTRAM_API_KEY": "agentram_your_key_here" }
    }
  }
}

Exact flags and config paths can shift between Claude Code versions. If a flag is not recognized, check Claude Code's current MCP docs. The server command and env var stay the same.

Quick start

Restart Claude Code so it picks up the server, then try it:

Store my project deploy command as "netlify deploy --prod" under the key deploy_cmd.

Later, in a new session:

Recall deploy_cmd from AgentRAM.

Smoke test and troubleshooting

Give your agent memory

AgentRAM is a simple memory API for AI agents. One call to store, one to recall, shared across agents, no vector database. Store your first memory in about a minute.

Get your API key

1,000 free operations. No credit card.

© 2026 AgentRAM. All rights reserved.