Where knowledge is forged, not forgotten. Thoughtful software for everyday life and enterprise.
Most AI companies optimize for engagement, growth, and data extraction. We optimize for helpfulness, simplicity, and trust.
Simple, ethical apps for everyday life. No dark patterns. No exploitation. Just helpful tools that respect your time.
Learn moreIntelligent systems for business workflows. Reduce costs. Increase capability. Maintain trust.
Learn moreA memory substrate under measurement. We test our own claims with pre-registered experiments—and publish what the benchmarks say, including when they say no.
We built a biologically inspired memory system, then ran it against strong baselines under pre-registered pass/fail criteria. The retrieval hypothesis failed its test—so we closed it and said so. What survived is a substrate for memory you can audit.
Retrieval thesis: closed
Graph vs. similarity, measured head-to-head. Similarity won; we published it
Substrate integrity: kept
Bit-identical replay, WAL durability, crash recovery, full provenance
Now testing: consequence at encoding
Causal annotations inside the representation—pre-registered, publish either way
In design: memory that acts
Wake conditions and evidence-carrying answers, gated on validation
Research Update: We Tested Our Retrieval Thesis. It Failed. Here’s What Survived.
Pre-registered experiments closed ngramDB’s founding retrieval hypothesis — embedding similarity beat our causal graph on every instrument, and we published the numbers. What held up: replayable storage, typed causal extraction, and full provenance. What’s next is gated on validation.
Article Series: Governing the Agents That Govern Themselves
A five-part series on AI governance, structural enforcement, adversarial testing, and the ethics of autonomous agent failure modes.
AURA — Self-Improving AI Agent (Beta)
Introducing AURA: an autonomous agent that continuously improves codebases, governed by immutable constitutional constraints and powered by ngramDB memory.
ngramDB — Neuro-Biological Memory for AI (Beta)
Introducing ngramDB, our biologically inspired memory research substrate. (Update, Aug 2026: the retrieval claims in this announcement were later tested and closed — see the research update above.)
Enterprise AI Solutions
EngramForge enterprise product suite now available — intelligent systems that remember context, learn from interactions, and improve over time.