Corvus
A persistent personal AI agent — semantic memory on local Ollama embeddings, hybrid Python + LLM execution, and cron-driven daily briefings. Privacy-first, runs on a Mac Mini.
Agent orchestrationLocal embeddingsPythonMemory design
The work.
Four ventures you can engage, and the systems behind them. I build what I recommend — these are real, running, and most of them I use every day.
Ventures — ways to engage
ConsultingActive
Velocity Partners
Making AI actually work inside organizations.
VisitTeachingLaunching Jul 2026
Get Hired Now Academy
AI & Claude Code courses for senior career-changers.
VisitPublishing2,100+ subscribers
Resilient Tomorrow
Practical resilience for people exiting the default.
VisitProductHeading to Product Hunt
Distills
Your career, as an interactive AI.
VisitAI Systems & Agents
AI Memory System
A cross-AI JSONL memory layer I built because no tool had one — Claude had no persistent memory, ChatGPT's couldn't be exported, my local model's couldn't be reached. A shared ledger (plus a validation agent) gives all three persistent, shared context.
RAGJSONLContext engineering
OfflineAI / Local LLM
A privacy-first, self-hosted LLM stack — Ollama, OpenWebUI, and an MCP bridge, auto-starting and always on.
OllamaSelf-hostedMCP
Mission Control
An operations dashboard for a fleet of AI agents, with ADHD-aware UX — a "Three Things" focus widget, brain-dump triage, and a signal-filtered activity feed.
Dashboard UXAgent opsSignal-to-noise
Agent Executive Suite
A multi-agent org structure — a chief-of-staff agent plus ops, sales, and product agents coordinating across every venture.
Multi-agentOrg designDelegation
Infrastructure & Self-Hosting
Apollo Media Server
A fully self-hosted media stack — Jellyfin, Radarr/Sonarr automation, VPN kill-switch, mergerfs storage, Tailscale remote access — documented so anyone can run it.
DockerLinuxStorage architectureVPN
Local Voice Control
A privacy-first home voice system — Home Assistant + Wyoming with on-prem speech, routing deterministic commands locally and complex queries to a local LLM.
Home AssistantWyomingLocal LLMPrivacy by design
Community & Real-World
Home Solar Array
A DIY-designed residential solar + 32 kWh battery system — full energy modeling, structural and permitting work, phased rollout, at a fraction of installer cost.
Energy modelingSystems designPermitting
NeighborhoodShare
A neighbor-to-neighbor tool-sharing platform — snap a photo and AI catalogs the tool down to brand and model. It reached 170 users across 20 communities before I wound it down: tool-sharing proved too infrequent to stay top-of-mind. I'm folding the idea into a larger, multi-purpose community platform.
ReactGPT-4o VisionGo-to-market
Want something like this inside your org?
That's exactly what Velocity Partners does.
Start a conversation