Experiment: NemoClaw
NemoClaw is not my project. It is NVIDIA's stack, announced at GTC, that wraps OpenClaw with enterprise guardrails: OpenShell sandboxes the agent, Nemotron models run locally on RTX hardware, and a privacy router decides what stays on-device and what goes to the cloud. I explored it to understand how sandboxing and on-device inference change what an autonomous agent can safely be allowed to do. It is listed here as an experiment with someone else's tool, not as something I built.
Built in public to learn something or prove a pattern. Some are published packages, some are demos that live on this site.
Experiment: NemoClaw
- ▸Understanding how sandboxing constrains an autonomous agent without making it useless
- ▸How work is split between on-device and cloud inference for privacy
- ▸Explored OpenShell sandboxing and the privacy router
- ▸Looked at local Nemotron inference versus cloud calls
A first-hand look at enterprise guardrails for agent frameworks
JobJam.io — AI Job Search & Application Platform
AI-powered job search platform: discover roles, evaluate fit, tailor applications, and close skill gaps. One-time pricing, no subscriptions.
Fathohm — Comprehension-Debt System of Record
See how much of your codebase no human understands. A treemap of your repo colored by human comprehension score, with a tracked, assignable metric for 'who understands what' in an AI-native codebase.
Grenz — Firewall for AI Agents
A local firewall for AI agents: scoped, revocable, observable permissions instead of your full GitHub token. Deny-by-default, MIT licensed, live at grenz.dev.