Focus on the things you love.

Vellum is a personal AI assistant that lives on your computer. It has its own identity, its own email, and the ability to take real actions for you like sending emails, managing your schedule, building apps, ordering food, browsing the web, and more. It learns who you are over time and gets better the more you use it.

ChatGPT and Claude are conversation tools that someone else controls. You type, they respond, and you copy-paste the answer somewhere else. You don’t own them, you don’t shape how they work, and they forget you between sessions. Vellum is different. It runs locally on your machine, you mold its personality and preferences, and it remembers everything about you over time.

OpenClaw is a powerful open-source agent built for developers and power users. Vellum is built for everyone, with a native macOS app, guided onboarding, and a permission system that asks before it acts. Where OpenClaw gives you full autonomy with fewer guardrails, Vellum requires your approval for every action until you decide to trust it.

Vellum uses a prepaid credit balance: usage is deducted as you use the assistant, and you can add credits from Billing. See pricing docs.

Your workspace, memories, and credentials are stored locally on your machine and never leave your computer. Your conversations are sent to a cloud AI model provider like Anthropic to generate responses, but nothing is stored on our servers. We’re transparent about that trade-off.

No. Your data is never used for training or fine-tuning from our side. For the AI model provider’s data policies, we recommend reviewing their terms directly.

Email, calendar, Slack, web browsing, food delivery, image generation, coding, app building, document writing, task management, phone calls, and more. Vellum ships with 60+ skills out of the box, and you can build custom ones to extend it further.

With your permission, yes. Vellum can see your screen and interact with UI elements through macOS accessibility and screen recording permissions. Both are opt-in and require explicit system-level approval before they’re enabled.

macOS for now, supporting both Apple Silicon and Intel. Windows and Linux are on the roadmap.