Cursor Memory
Long-Term Context for Cursor AI IDE.
Connect your Cursor Composer and Chat environments to your personal memory vault. Inject style rules, remember architectural patterns, and speed up composer code generations.
Accelerate Your Cursor Composer Workflows
Cursor is one of the most powerful developer editors, utilizing agent loops (Cursor Composer) to edit multiple files concurrently. However, Composer sessions consume a massive volume of tokens when reading codebases, leading to high latency and cost.
Memwyre optimizes your Cursor setup. By indexing your design decisions, guidelines, and conventions into our memory graph, Cursor's LLM retrieves only the exact context it needs, bypassing large index scans. The result is a sub-300ms retrieval speed that keeps Composer runs fast and focused.
Core Integrations
Automatically inject coding rules, database schemas, and API constraints into Composer sessions.
Save money on index rebuilding. Memwyre local cache answers key structural questions instantly.
When saving memories, Memwyre links them directly to Cursor codebase references (files, symbols).
Prunes out intermediate logs and command errors from the composer buffer to avoid cluttering attention.
Cursor MCP Setup
Add the Memwyre server in Cursor settings:
- Open Cursor Settings -> Features -> MCP.
- Click + Add New MCP Server.
- Configure with:
- Name:
memwyre - Type:
command - Command:
npx -y @memwyre/mcp-server
- Name:
- Add environment variable:
MEMWYRE_API_KEYwith your key.
Sync Context to Cursor
Start building your personal long-term AI memory graph. Save context in the browser and use it in your IDE.