Ulpia https://ulpia.io/blog/ 2026-09-16T00:00:00Z Why In-Process Memory Beats Resident Daemons: Lessons from the AI Memory Frontier https://ulpia.io/blog/why-in-process-memory-beats-resident-daemons/ 2026-09-16T00:00:00Z Richard Wollyce Exploring the architectural tradeoffs in AI agent memory: why in-process SQLite FTS5 beats resident server daemons, how filesystem boundaries prevent multi-tenant leaks, and what is coming next in Ulpia. From Prototype to Production: 5 Architectural Upgrades in Ulpia's RAG & Multi-Agent Engine https://ulpia.io/blog/from-prototype-to-production-rag-and-agents/ 2026-09-14T00:00:00Z Richard Wollyce Five architectural upgrades turning naive RAG into a production engine: small-to-big section windowing, constitutional critique ledgers, cross-domain query decomposition, offline triad grading, and 4-bit AWQ student distillation under 2 GB RAM. Our system doesn't need a model to do the retrieval https://ulpia.io/blog/our-system-doesnt-need-a-model-to-do-the-retrieval/ 2026-09-03T00:00:00Z Richard Wollyce The first video on the channel: why I decided to build Ulpia, why AI memory should be local, and why retrieval here does not go through a model. The confidence floor now scales with your corpus https://ulpia.io/blog/the-floor-scales-with-the-corpus/ 2026-09-02T00:00:00Z Richard Wollyce Why one threshold cannot serve a base of ten notes and a base of a thousand, every term in the formula spelled out, and the three measurements the change had to pass before it shipped.