MonkeyLLM

MonkeyLLM

**A knowledge engine for AI agents: a new way to query your data.** Your documents become a git-versioned markdown knowledge graph an agent navigates over MCP: curated summaries, typed edges, cited answers, SQL over your spreadsheets, nothing chunked into anonymous fragments.

This repository is **not an application**. Knowledge lives in a **forest**: a git-versioned tree of markdown nodes, each carrying a curated, scent-bearing passport. An AI does not get handed a retrieval dump. It **navigates**: drops in through search, follows typed edges, reads exactly the node it needs, and plants what it learns. Successful hunts deposit pheromone and mint shortcut links, so the corpus itself learns from use.

A real forest: 1,877 nodes across 49 branches. Every cluster is a branch, every dot a node; solid lines are curated trails, dashed ones are shortcuts a hunt discovered, and the glow is pheromone left by use.

The number that made us write it down: on a benchmark where **every question needs ≥3 chained hops**, the *same* 12B local model scores **0 / 11 as a classic top-k RAG reader** and **11 / 11 (100%) as a forest navigator**, at **0.66×** the token cost per correct answer of an iterative-RAG baseline, on a single consumer GPU. If your fir