Enables AI agents to locally search, query, and understand codebases with token-efficient context, dependency graphs, history, architecture diagrams, and metrics through MCP.
Provides ephemeral hybrid (vector + BM25) memory for MCP-compatible editors, enabling AI to save and search conversation and code context across sessions with automatic semantic search and context injection.
Enables AI coding agents to intelligently index and search codebases with sub-20ms retrieval, 8x memory compression, and cross-encoder reranking via MCP stdio.