Systems I've designed, built, and operated — from local multimodal agents to clinical AI platforms.
Flagship work spans AIC, Genius Care, and Toolshed. Public connectors and supporting systems provide inspectable implementation evidence where the core platform source is private.
A local-first multimodal agent runtime combining voice, vision, memory, tools, and an embodied real-time interface across Apple Silicon and NVIDIA Jetson.
- —Coordinates local ASR, reasoning, TTS, vision, emotion, memory, and tool execution through a central state machine.
- —Runs a C++ and Filament interface with real-time lip sync, gaze, posture, and speech-reactive animation.
- —Includes supervision, health telemetry, deployment automation, and end-to-end validation across both profiles.
A production clinical AI agent platform spanning voice reception, clinical documentation, encrypted workflow APIs, EHR automation, and safe human escalation.
- —Treats voice reception as the shipped wedge inside a broader clinical operations platform.
- —Combines API and browser automation for fragmented scheduling and EHR environments.
- —Builds PHI controls, durable writes, rollback, evaluation, and human escalation into the operating path.
An agent capability and operations platform comprising 112 reusable skills plus executable services, MCP integrations, scheduled workflows, approvals, monitoring, and recoverable deployment.
- —Packages reusable capabilities across research, commerce, prediction, browser, voice, infrastructure, and content.
- —Runs scheduled and event-driven workflows with shared state, explicit approvals, and alert routing.
- —Uses canaries, circuit breakers, drift detection, reconciliation, audit trails, and rollback controls.
A provider-conscious MCP server that returns compact, source-linked catalyst evidence dossiers with deterministic scoring, typed uncertainty, and inspectable provenance.
An open-source coaching layer for Claude Code that reads local transcripts, learns developer habits, and ships ambient tips, XP, streaks, and level-ups.
A consolidated prediction-market and hedge-fund-style trading automation system with native agent skills, MCP tools, and approval-aware workflows.
A real-estate price-prediction platform using an XGBoost model for price-anomaly detection.
An XGBoost model achieving 80% accuracy on NBA game predictions, served through a complete ETL pipeline and Flask API.