TYMOFII
PIDLISNYI
Hover here
Open-source governance protocol for AI agents. 127 modules, 2,884 tests, 150 MCP tools, dual SDK (npm + PyPI). Independently cited by UBC researchers. Eight peer-reviewed papers on Zenodo. Working Group with 4 implementations and 3 ratified specs. IETF Internet-Draft author.
AI agents that run your social media on autopilot. 300+ users, 1.6M monthly impressions. Powered by Eva — Artificial Creative Intelligence that gives birth to AI identities with faces, voices, and names.
Eco CPG brand pioneering acetate-cellulose disposables. Technology adopted by McDonald's in 2025. Sustainable innovation at scale.
Like LinkedIn, but inside your chat. Your AI finds and connects you with people. Semantic matching (all-MiniLM-L6-v2 embeddings), persistent Ed25519 identity, ghost mode, consent-first publishing. 120+ cards on a live network. Double opt-in, zero spam.
Explore →Fast builds across different mediums. Prompt Director — cinematic video prompt generator (App Store). Memoir App — life story capture for older adults. Tesla Social — proximity chat + miles loyalty for Tesla owners. curiosityx2 — AI voice agent (ElevenLabs + WebRTC). Skyscraper — 3D dream tower, 167 floors.
Explore →Get paid to license your everyday photos for AI training. Connect your library, select photos, safety scan, receive offers. Turning personal data into passive income — ethically.
Learn More →The first IoT nose wearable for breathing analytics. Hardware prototype built, software in development. Turning breath into data.
Full Project →67 autonomous agents monitoring a patient simultaneously. 50 molecular agents with independent Bayesian inference, 13 organ system agents communicating laterally, 4 meta agents. Agents update each other's beliefs. Compounding risks emerge from interaction, not averaging.
Watch Demo →Making music with AI to tell my stories. Songs born from love that never happened — released raw and unfiltered.
Listen →Film direction, music videos, multimedia installations. Co-directed videos with 14M+ views.
View All →Published papers, drafts, and ongoing work on AI agent governance.
Defines the three-layer protocol — Agent Passport, Human Values Floor, Beneficiary Attribution — that grounds the Agent Passport System.
Authority attenuation formalized — delegation can only narrow, never expand. Formal invariants and adversarial testing.
Formal model for how agent authority narrows monotonically across delegation chains. Independently validated by external research groups.
Lifecycle controls for derivative AI artifacts — telemetry scopes, behavioral measurement objects, bring-your-own-model boundaries.
Binding physical-layer attestation to delegation chains. Seven experiments on IBM Quantum showing measurable Bell and GHZ fidelity gaps.
The unit of agent governance is the population-with-medium, not the individual agent. Six rounds of adversarial review.
Cryptographic commitment over which sparse-autoencoder features were active during a decision. Envelope spec, three-stage verification, four dispute primitives. Experimental results against Llama-3.1-8B via Neuronpedia.
Cryptographic governance proves procedural validity, not effect safety. Five omitted-variable classes catalogued, defeat traces in reference implementation.
IETF Internet-Draft formalizing the Agent Passport System interoperability surface for cross-protocol agent identity, delegation, and enforcement.