Cursor10x Memory
A memory system for Cursor that provides persistent context awareness for Claude through vector-based semantic search and structured data storage. Built by aurda012 using Turso/LibSQL as the backend, it stores conversations, code snippets, files, and other contextual information with automatically generated embeddings for similarity-based retrieval. The implementation includes unified conversation management tools that handle message storage, context retrieval, and milestone tracking in single operations, plus vector indexing with ANN search capabilities for efficient semantic matching. Designed for developers who want their AI assistant to maintain long-term memory across sessions, enabling workflows like project continuity, code pattern recognition, and contextual assistance based on previous interactions and codebase knowledge.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/aiurda/cursor10x-mcp
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Cursor10x Memory from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.