AlphaGo-inspired MCTS for document retrieval. No vectors, no embeddings, no chunking — just reasoning. Upload PDFs, ask questions, get answers with citations.

Vectorless, reasoning-based code index cho AI context retrieval. Instead of dumping your entire codebase into a prompt (50k+ tokens), codeindex builds a hierarchical tree index and uses LLM reasoning to find the exact context you need

Hosted MCP server + slim wiki projection of the First Principles Framework (FPF) by Anatoly Levenchuk. Bounded, vectorless retrieval over 292 patterns and 3 curated routes — addressable by stable FPF IDs, synced daily from ailev/FPF.

A retrieval engine that reasons over document structure — not embeddings. No chunking, no top-K, no vector DB.

Code-aware search and navigation engine, powered by vectorless.

A vectorless RAG pipeline that navigates PDF documents using a PageIndex tree structure and Gemini 2.0 Flash — no vector database, just LLM-guided tree search with auto-cited answers.

Documentation site for Vectorless — document retrieval for the reasoning era. Fumadocs, deploys to docs.vectorless.store.

Vectorless, reasoning-based RAG (PageIndex) in JavaScript. Runs in the browser via WASM and anywhere JS runs.

Vectorless RAG via hierarchical tree indexing — Go reimplementation of PageIndex with zero external deps

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.

Agentree: index PDFs into a hierarchical section tree for agent retrieval (Claude/Codex structured completions, not vector chunking).

Deliver precise document retrieval using Monte Carlo Tree Search for PDF and folder-based question answering without vectors or embeddings.