Build. Test. Question.

Perception. Interpretation. Action.

A selective view of experimental software and technical inquiry. We report working mechanisms, measured findings, and limitations separately. Source implementations remain private unless deliberately released.

Research / Public overview

Resident Model Lab

Local OLMoE inference with router-faithful expert residency. Compare the v0.2 memory, latency and fidelity findings with their experimental limits.

Read Resident Model Lab methods and limitations →
Research / Public overview

Research Stack

Public research software v0.1.0: TRACE · LOOP · LENS · FRAME connects provenance, evaluation, visualization and reviewed corrections. Includes NRS-Bench, three technical reports and 54 developer/CI-reported tests on controlled synthetic evaluations, not a real-model or human study.

Read Research Stack methods and limitations →
Research / Public overview

VEYDRIS

Recorded-video detection, temporal tracking, replay and exports in a local prototype. The synthetic map is not verified geolocation.

Read VEYDRIS methods and limitations →
Research / Public overview

Human–AI interaction & explainable AI

Evidence provenance, conversational memory and inspectable uncertainty, with founder-led Epistemic Trust Lab synthetic-policy evaluation kept distinct.

Read Human–AI interaction & explainable AI methods and limitations →
  1. /01Perception

    Sensing & classification utilities

    Small, non-sensitive examples of signal handling and object classification pipelines.

  2. /02Inference

    Evaluation & orchestration patterns

    Reference patterns for evaluating models and composing intelligent workflows.

  3. /03Oversight

    Human-in-the-loop interfaces

    Interface studies for reviewing machine recommendations before action.

  4. /04Explainability

    Inspectable AI Interfaces

    Interface patterns for transparent model explanations, uncertainty, evidence provenance, and human correction or override.

Visit GitHub (opens in a new tab)

Company research is described here without disclosing unpublished source code or private experimental materials.