The work

Things I'm working on..

The tools and products I'm building around AI agents — each one real and in use.

Projects

Public-facing products and platforms.

Kernel

Turns AI agents into a governed organization

The runtime underneath much of this page. Each domain of work becomes a node run by its own scoped AI operator — on a charter, a heartbeat of scheduled autonomy, and tiered permissions enforced mechanically, so consequential actions wait for a human signature: the agent doesn't just promise not to overstep, it structurally can't. I set direction and approve what matters; Kernel runs the operation. Ships as a self-contained runtime with a signed desktop app.

Appleo

Chat your resume into existence

An AI agent that clears the mechanical half of a job search. Appleo writes and versions your résumé, tailors a copy to every listing and scores the fit, tracks your applications, and renders clean, ATS-ready PDFs — with a public share link when you want one. You talk; it handles the paperwork; the search stays yours.

appleo.ai Read more

Decorum

Conduct & persona for AI agents

The lines your agent won't cross, and the voice it speaks in. You declare conduct (what it may say and do) and persona (how it sounds) in one policy source; Decorum compiles both into the model's prompt and into mechanical, fail-closed floors on input, tool calls, and output. Prompt asks; structure guarantees. Licensed per deployment and run entirely on your own infrastructure — already enforcing in production, including behind Appleo.

decorum.systems

Assay

Token ROI for AI work

To assay is to test ore for its precious metal. Assay does that to AI spend: it meters every token an agent burns, seals the transcript that drove the spend, and joins the two — what a result cost, where the waste is, what the tokens were actually worth. Running inside my own stack today; next it takes the same commercial shape as Decorum.

CastCard

An AI-discoverable identity platform

A professional profile at an @handle that AI assistants can actually find and answer questions about — backed by structured data, a REST API, and an MCP server, so ChatGPT, Claude, and the rest know who you are.

castcard.ai

Sovereign SDK

The open core of my agent runtime

An embeddable, MIT-licensed agent-loop engine: createAgent() gives you the turn loop, typed fail-closed tools, streaming, and provider routing across cloud models or a local Mac lane, with a persistent learning layer on top. The engine that became Kernel's agent core — and the open packages are yours to build on.

yevgetman/sovereign-ai-sdk

Tools

The smaller utilities I built and use every day.

sitekit sites · in use

Tool for sites. An LLM writes the page; sitekit holds it to a versioned voice, style, and shape — build, verify, deploy, maintain — so the site stays on-brand as it grows. This site runs on it.

telekit telegram · in use

Tool for Telegram. A live bridge between my phone and my AI stack — inbound messages become governed agent turns, replies stream back, and nothing sends without an explicit yes.

calkit calendar · in use

Tool for calendar. My calendar as version-controlled YAML — recurring events, agenda views, iCalendar import and export — so scheduling gets a git history and an agent can manage it safely.

mailkit email · in use

Tool for mail. Gives an LLM safe, deterministic control of Gmail — read, search, draft, organize, send (with a confirmation step). The alignment-layer idea, pointed at my inbox.

voicekit writing · open source

Captures how I write and reproduces it — drafts in my voice, then scores the result against my own fingerprint. The agent on the home page sounds like me because of it.