01Projects7 systems
Systems built to survive real users.
Voice agents, AI defense layers, coding-agent infrastructure, and trading research. Different domains, same job: take a strong model and build something around it that holds up in production.
01Voice AI Receptionist→A phone-first intake system for non-emergency patient transport, combining telephony-aware ASR, explicit eligibility logic, structured capture, and safe handoff to human operators.Active client workVoice AI02Houseparty→Houseparty runs coding agents as persistent, supervised sessions instead of throwaway subprocesses, with PTY-backed terminals, shared memory, and resumable runs.Open sourceAgent tooling03Hannah→Hannah sits between coding agents and the model API and rewrites only the expensive parts, cutting wasted tokens while leaving the cheap passthrough alone.Open sourceDeveloper infra04Norse3→Norse3 is an AI defense layer that sits in the live message path for support and chat. It makes a policy decision on every message, writes privileged moderation actions under a verifiable identity, logs incidents, and gives human operators a review surface.Case-study readyAI defense05Ashlock Trading→Ashlock is a three-strategy trading research stack: separate capital per strategy, live options, order-book research, and a shared validation layer that keeps the numbers honest.Active research + live optionsResearch systems06BM-Bench→BM-Bench asks a question most simulator papers skip: does a simulator that matches the market statistically also train agents that work on real data? The answer, measured across three simulator classes and nine trained reinforcement-learning agents, is no — and the gap between the two is the finding.Preprint — working draftResearch07Mycelium→Mycelium turns idle laptops and workstations into a private inference pool, so a team can serve its own models without the cloud bill or the DevOps.PlannedInfra concept