A semantic code retrieval engine for AI agents that enables hybrid search, graph expansion, and token-aware context packing, integrating with MCP to provide precise code context to LLMs.
Enables Claude Code and AI coding agents to retrieve compact, task-shaped code evidence bundles via MCP, combining AST-aware retrieval, hybrid BM25+FAISS search, call-graph traversal, reranking, and token-budgeted context assembly.
Enables coding agents to retrieve the most relevant code for a task within a hard token budget by fusing code graph, BM25, local embeddings, and git history, and to navigate symbols, callers, impact, and related files. It runs locally over MCP with no API keys and keeps its index fresh.