Reasoning beyond isolated interactions
Exploring how a system could keep its purpose and understanding across interactions, instead of starting over with every prompt.
JUSTMYTH · AI RESEARCH
Toward the boundless.
JustMyth is an AI research lab building efficient, auditable reasoning systems, and the software people use them through.
Research · PROJECT Z/01
Architecture before scale.
Our research asks a simple question: how much intelligence can be produced by better structure before adding more brute-force compute?
Project Z/01 is an experimental AI research initiative exploring systems that can reason beyond isolated prompts, adapt through experience, and operate with greater continuity and accountability. Our ambition is to investigate new foundations for intelligence that is efficient, reliable, and guided by verifiable evidence.
These are research objectives, not proven capabilities.
Adaptive learning and knowledge development
Investigating how understanding might grow through experience over time, while remaining open to review.
Efficient intelligence
Asking how much capability can come from better foundations, rather than from ever more resources.
Accountability, reliability, and human oversight
Aiming for behavior that can be examined, depended on, and kept under meaningful human direction.
- Pre-alphaMythBrowseAI-first desktop browserA Windows-first browser on the Servo engine, all Rust, where a conversation is the home screen. The open build is on GitHub.
- Pre-alphaMythDeskLocal-first personal AI agentAn agent that works on your real Windows PC and asks before anything risky.
- In developmentMythSheetRust-native data workspaceFamiliar cells and formulas, with analysis and inspectable AI assistance in the same workspace.
Mission
Intelligence should not end at a prompt.
We believe progress in AI should be measured not only by the answers a system produces, but by the rigor, efficiency, and reliability of the mechanisms behind them.