
Stores and retrieves context in LaightDB via MCP tools (hybrid search, get by id, collections, stats). Use when the user connects the LaightDB MCP server in Cursor, wants to save project/session context for later, or asks to search or load previously stored LaightDB context through MCP.
Build an LSM-tree storage engine in Go with WAL, MemTable, SSTables, bloom filters, and compaction. Use when implementing or modifying internal/storage/ components, writing the WAL, MemTable, SSTable, compaction, or the storage engine orchestrator.
Build MCP servers using the official Go SDK (github.com/modelcontextprotocol/go-sdk/mcp). Use when implementing MCP tools, resources, server setup, transport configuration, or anything in internal/mcp/.
Vite/React UI for LaightDB: dashboard, search, and the 3D Explorer (/explorer) for context graphs and storage engine layout. Use when editing ui/src, Vite config, or REST client calls for graph overview / storage diagnostics.
Generate text embeddings with gobed and use coder/hnsw for vector search. Use when working on internal/embedding/, internal/index/vector.go, or implementing vector similarity search.
Proactively loads relevant LaightDB context at the start of substantive work and persists concise rolling notes before wrapping up, using LaightDB MCP tools without waiting for the user to say "store" or "search". Use whenever this workspace has the LaightDB MCP server enabled and the user is doing multi-step implementation, debugging, or design that should survive across sessions.
Proactively loads relevant LaightDB context at the start of substantive work and persists concise rolling notes before wrapping up, using LaightDB MCP tools without waiting for the user to say "store" or "search". Use whenever this workspace has the LaightDB MCP server enabled and the user is doing multi-step implementation, debugging, or design that should survive across sessions.