Exposes a codebase's symbol graph and symbol-aware editing tools to AI agents, enabling targeted symbol lookup, impact analysis, and atomic multi-file edits with reduced context tokens.
Enables token-efficient local code retrieval by indexing a codebase once with tree-sitter and serving exact symbol bodies on demand, avoiding whole-file reads.
Enables LLM agents to efficiently understand and navigate a codebase by providing semantic search over symbols and a reference graph, replacing expensive grep/glob calls with structured tools like definition lookup, caller/callee queries, and change-impact analysis.