> initializing agent.fleet

Security architect · autonomous AI you can trust

I build the systems that build.

Not web apps — autonomous agents. I'm a security architect who builds AI that can actually take actions: a governed fleet that researches, reviews code, and self-heals on a local-first stack — with the sandboxes, kill-switches, and spend gates that let it run unsupervised without going off the rails. Autonomy you can trust, because I built it to be trusted.

Founder @ DCYFR Labs  ·  Head of AI@ GameShark Labs  ·  remote

6+ yrs security architecture  ·  25 certifications  ·  @dcyfr/ai on npm  ·  products shipped, built by agents

fleet.stream30+ agents24/7 autonomylocal-first inferencecost-gated

Selected work

Systems that run themselves.

Not a stack of frameworks — the autonomous machinery I've built, shipped, and keep running.

01

DCYFR AI

The portable TypeScript runtime my agents think in — model routing across local and frontier tiers, tool-use, and MCP wiring you drop into any project.

Agent runtimeTool-useMCPTypeScript
Open
02

Agent Governance & Safety

The rails that let agents take real actions without going off the rails — sandboxes, kill-switches, per-process credential isolation, and enforced spend limits. Autonomy you can trust.

AI safetySandboxingKill-switches
Live
03

Autonomous Agent Fleet

A governed swarm of AI daemons — research, code review, monitoring, self-healing — running a 30-minute cognitive loop on a local-first model stack, under a hard spend gate with metacognition to stop it spinning.

Multi-agentLocal-first inferenceSelf-healingMetacognition
Running
04

SharkVault

Proof the fleet ships real product: a backer-funded consumer app taken end-to-end — auth, payments, content pipeline — largely by agents.

Autonomous deliveryProductNext.js
Live

Ventures

What I lead

Writing & garden

Field notes from the frontier.

Essays when they're finished; a digital garden of evergreen notes while they're still growing.

Now · last synced Jul 2026

Current focus

Teaching the fleet to plan. Multi-step missions the agents decompose, execute, and grade themselves — with me out of the loop.

Raising the trust ceiling. Hardening the safety model so agents can take higher-stakes actions without a human gate on every step.

Work with me

Ship autonomous AI you can trust.

I build and secure autonomous AI systems for teams shipping to production — from your first safe agent to a governed fleet.

Fractional builds

I embed and build your agentic systems end-to-end — the runtime, the agents, and the guardrails — then hand you something you can actually run.

Safe-autonomy audits

You've got agents that can take actions. I pressure-test the sandboxing, permissions, and spend controls before they cost you — the OWASP-for-agents review, done right.

Advisory

Ongoing help pointing your team at the agentic frontier without the footguns — architecture, model routing, safety, and what's actually worth automating.

Let's build something autonomous and hard to break.

20 min, no pitch — tell me what you're trying to automate, and I'll tell you if it's safe to.