AlphaGo-inspired MCTS for document retrieval. No vectors, no embeddings, no chunking — just reasoning. Upload PDFs, ask questions, get answers with citations.
-
Updated
Mar 10, 2026 - Python
AlphaGo-inspired MCTS for document retrieval. No vectors, no embeddings, no chunking — just reasoning. Upload PDFs, ask questions, get answers with citations.
Code-aware search and navigation engine, powered by vectorless.
MAXXKI CodeIndex: A vectorless, AST-based RAG framework for local code analysis. Leverages hierarchical LLM routing and abstract syntax tree indexing instead of vector embeddings. Provides precise, local-first code Q&A without the overhead of vector databases. MAXXKI CodeIndex — Local-first, offline code intelligence for Python codebases. Ask natur
Find code context 4.6x faster and 9.6x cheaper than Pi on Codebase QA.
A vector-less RAG works fully in local NO internet needed, with webUI
Vectorless, reasoning-based RAG that runs 100% on-device (Ollama + Qwen) — grounded answers with a 0–100 confidence score that abstains when unsure.
To associate your repository with the vectorless topic, visit your repo's landing page and select "manage topics."