Retrieval beats dumping your KB into context
NovaCortex fetches only the few facts a question needs. Dumping the whole knowledge base into every prompt burns tokens, money, and (with a hosted provider) ships all your data every time. Same questions, same model — here is the measured difference.
The numbers
| KB size | Dump tok | Retrieval tok | Reduction | Dump cost | Retrieval cost |
|---|---|---|---|---|---|
| 42 facts (~2K) | 2,028 | 305 | 85% | $0.0048 | $0.0009 |
| 220 facts (~10K) | 10,157 | 305 | 97% | $0.0231 | $0.0009 |
| 560 facts (~26K) | 25,675 | 305 | 98.8% | $0.0581 | $0.0009 |
15 questions, gpt-4o-mini, top-5 retrieval, costs for the full 15-question run. Answer accuracy (LLM-judged against reference answers): dump 100%, retrieval 93%. Retrieval recall@5 = 100% even with 518 unrelated distractor facts in the store — NovaCortex surfaced every fact the questions needed.
How we measured
Two ways of giving the model the project knowledge: dump the whole KB into the prompt every query, or store it in NovaCortex and retrieve only the top-5 relevant memories. We score retrieval separately with a recall@K metric, so the rare answer miss is shown to be an LLM/grader limit (it hits the dump baseline equally), not a retrieval failure. Fully reproducible: node scripts/benchmark/run.mjs.
And it's a privacy win, not just a cost one
Dumping the whole KB ships all of your knowledge to the model provider on every query. Retrieval sends only the few relevant snippets. With NovaCortex self-hosted, the knowledge base never leaves your infrastructure; only the minimal retrieved context goes to the model.