Do You Need Embeddings? A Decision Guide
Signals that lexical search over curated metadata will carry you, signals you genuinely want vectors, and a fifty-query gold-set test to settle it on your own corpus before paying for infra.
4 min read
Blog
Notes from the forest
Engineering notes on navigation, ingestion, agent memory and honest benchmarking, written by the people who ran the experiments.
Ingesting 100 Real Documents: The Write-Time Trade
Ingest is where the forest spends its effort: 1.71 s per document, a sixty-token summary contract passed at 100%, zero broken links. Pay once at write time, in a batch you can watch, instead of on every query forever.
4 min read
Run It Without a Local GPU
The benchmark rig is one RTX 3060, but nothing requires you to own a GPU. Point the chat binding at any OpenAI-compatible endpoint and let the forest do the structural work.
4 min read
From Zero to a Grounded Answer in Ten Minutes
Four commands to deploy, one screen to claim it, one folder to ingest, and a first answer that arrives standing on the exact nodes it read. Your first ten minutes with a knowledge forest.
4 min read
Self-hosting MonkeyLLM in 10 minutes with Docker
One container, two volumes, no external database. From a clean machine to a forest your AI can query, including the parts that matter on a VPS.
3 min read
Want the long version?
The paper carries the full architecture, the benchmark tables and the findings that failed their criteria.