Moneypenny‑AI
Always on. Impeccably discreet.
A personal AI assistant built on reliability, control, and quiet competence.
Always on. Impeccably discreet.
A personal AI assistant built on reliability, control, and quiet competence.
Your data stays within your environment. No training on your data. Ever.
Built for consistent performance, with monitoring, alerts, and redundancy.
Intelligent assistance that integrates seamlessly into how you work.
Just a personal AI assistant. Moneypenny is always on and chats in Finnish over WhatsApp, Telegram, Slack, Discord, and Gmail — sharp, witty, and proactive, true to her namesake.
She's built on NanoClaw, an open orchestrator core: one Node.js process handles the channels and queues, while the actual thinking runs in isolated containers on the Claude Agent SDK. All on my own hardware, transparently in the EU.
How a message flows through →A compact desktop AI supercomputer with 128 GB of unified memory runs the local coding and general-purpose models. Beside it, a silent Beelink N100 on Ubuntu Server hosts the always-on orchestrator stack — NanoClaw, PostgreSQL, Redis, and n8n.
Local models handle coding and everyday assistance; frontier APIs step in only when asked.
You decide what runs, where it runs, and who has access.
Defense-in-depth controls keep your data and prompts protected.
Route to the right model for the task, cost, and sensitivity.
No noise. No clutter. Just reliable assistance when you need it.
$ moneypenny login Opening browser to authenticate… ✓ Signed in as [email protected] ✓ Token stored in system keychain $ moneypenny chat "review this diff for security issues" Routing → Qwen3-Coder (local) Analyzing 3 changed files…
Authentication works like it should: moneypenny login opens the browser, I sign in with a passkey, and a short-lived token lands in the system keychain. No API keys to copy around.
Moneypenny-AI is designed to support your obligations under Regulation (EU) 2024/1689 — single-tenant deployments, full audit logging, and human oversight built in. Your data stays in your jurisdiction.
“The purpose of this Regulation is to improve the functioning of the internal market and promote the uptake of human-centric and trustworthy artificial intelligence (AI), while ensuring a high level of protection of health, safety, fundamental rights enshrined in the Charter, including democracy, the rule of law and environmental protection, against the harmful effects of AI systems in the Union and supporting innovation.” — Article 1(1), Regulation (EU) 2024/1689 (EU AI Act) · EUR-Lex