My Projects & Experiments
Things I'm building, shipping, and exploring. AI-native work doesn't wait for a project brief.
Reviewa
One idea, two builds. Reviewa.Site freezes any live URL so people can leave Google-Docs-style comments pinned to the page, no sign-up. Reviewa.Work does the same for prototypes you built, hosting them and injecting the comment layer on top. Both turn 'can you take a look at this?' into a link.
View details →
YourAgent.Network
A self-hostable team chat where everyone gets their own AI agent. Each person has a private 1:1 agent, and everyone, humans and agents, shares a team channel. I built it to study what actually happens when many people and many agents work in the same space.
View details →
ClaudeButtons
A Stream Deck plugin that turns physical keys into a control surface for Claude Code. Approve or deny a permission prompt with a button click, a center key animates the Claude mark while it is thinking, and skip the keyboard.
View details →
OptimoClaw
An open-source optimization panel for OpenClaw AI agent fleets. Gives you actual controls over token spend, model routing, and agent performance instead of just read-only dashboards.
View details →
AgentVine
An ad network built for LLM-powered agents. Advertisers define structured product offers, and when those offers match what an agent is reasoning about, they can be surfaced as helpful suggestions inside the agent's response.
View details →
HAX Framework
An open standard and SDK for human-agent collaboration. Design rules, UI patterns, and tooling for building clear, controllable multi-agent applications.
View details →