AperturePlus/augmented-codebase-indexer
Semantic level code search/indexer with tree-sitter parsing, Qdrant vector store, and Typer/FastAPI interfaces. Supports calling via MCP.
Indexes code at multiple semantic levels (function/class summaries, file overviews, code chunks) to support both high-level architectural queries and precise implementation searches. Implements hybrid search combining vector similarity with keyword filtering via path modifiers, enabling queries like `"auth handler -path:tests"`. Designed for agentic LLM workflows via MCP protocol, with Docker sidecar deployment pattern keeping codebases local while exposing search capabilities to Claude, Cursor, and other AI tools.
Stars
83
Forks
6
Language
Python
License
—
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/AperturePlus/augmented-codebase-indexer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
karadHub/jenkins-ai-optimizer
Meet the beast of Jenkins MCP with AI-powered diagnostics, and more with Industrial debugging...
starkbaknet/project-vectorizer
A CLI tool that vectorizes codebases, stores them in a database, tracks changes, and serves them...
userFRM/rpg-encoder
Repository Planning Graph — semantic code understanding via MCP (arXiv:2602.02084)
houtini-ai/fanout-mcp
A Query fan-out analyser for AI Search
IronAdamant/stele-context
Local context cache for LLM agents. 100% offline, zero dependencies.