Skip to content

← All guides

Archive memory guide

This Cursor guide is preserved for existing users. Memory is now supporting infrastructure under the production-action control product.

Current offersRisk Review

How to Add Persistent Memory to Cursor

Cursor is a powerful AI code editor, but it forgets project context between sessions. The Novyx MCP Server gives Cursor persistent memory — your AI assistant remembers your codebase, preferences, and decisions across every workspace.

The Problem

  • ✗ Cursor forgets project context when you close a session
  • ✗ You re-explain architecture and conventions every time
  • ✗ No way to search past decisions or context
  • ✗ No undo if the AI learns something incorrect

The Solution: Novyx MCP Server

The Novyx MCP Server exposes memory tools to Cursor via the Model Context Protocol. Cursor can store decisions, recall past context, preserve audit context, and recover supported state — all persisted across sessions.

Setup

1. Install the MCP server:

bash
pip install novyx-mcp

2. Add to your Cursor MCP config:

json
{
  "mcpServers": {
    "novyx-memory": {
      "command": "python",
      "args": ["-m", "novyx_mcp"],
      "env": { "NOVYX_API_KEY": "YOUR_API_KEY" }
    }
  }
}

Add this to your Cursor settings or .cursor/mcp.json in your project root.

What Cursor Can Do With Memory

Remember project architecture

"This project uses a microservices architecture with gRPC between services." — stored permanently.

Recall coding preferences

"What formatting conventions does this project use?" — instant recall from past sessions.

Track decisions

"We chose PostgreSQL over MongoDB because of ACID requirements." — never explain the same decision twice.

Recover mistakes

"Go back to the last good project-memory checkpoint." — supported recovery without treating every side effect as reversible.

MCP Tools Available

CategoryTools
Core Memoryremember, recall, forget, list_memories, memory_stats, rollback, audit, link_memories, add_triple, query_triples
Context Spacescreate_space, list_spaces, space_memories, update_space, delete_space, share_space
Replayreplay_timeline, replay_snapshot, replay_lifecycle, replay_diff
Experimental maintenanceOptional memory-maintenance helpers where enabled

See the full MCP server docs on the Integrations page.

Start with the production-action gate

For the current product path, start with a governed production action.

Run the gate