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.
Anatomy of a Node Passport
Title, sixty-token summary, tags, aliases: why the passport is where MonkeyLLM spends its intelligence, and how field-weighted BM25 turns curation into recall@5 = 1.00 at 1.3 ms.
4 min read
BM25 Over SQLite vs a Vector Database
The category assumes an embedding service, an ANN index and a GPU. We measured entry search at recall@5 = 1.00 at 1.3 ms p95 with BM25 over SQLite, and kept the embedder optional.
4 min read
Why the Trails Did Not Converge
Trail learning missed its convergence criterion: hops fell by roughly half the threshold. The post-mortem: why sharp entry search and disciplined curation left trails almost nothing to compress.
4 min read
Want the long version?
The paper carries the full architecture, the benchmark tables and the findings that failed their criteria.