FAQ

About the product

What is Vellum?

A personal AI assistant that lives on your computer. It can take real actions on your behalf: reading files, sending emails, browsing the web, controlling your Mac, building apps, managing your schedule, making phone calls, and more. It has its own identity, personality, and long-term memory that persists across conversations. See What is Vellum? for the full overview.

How is this different from ChatGPT or Claude?

Those are conversation tools. You type, they respond, you copy-paste the answer somewhere. Vellum is different because it has tools (it can actually do things on your computer and across services), memory (it remembers you across conversations with a full hybrid search system), a persistent identity (its own personality, name, and behavioral rules you can customize), and it reaches you everywhere (desktop, iOS, Telegram, Slack, WhatsApp, voice calls). More detail in What is Vellum?.

Is Vellum free?

You can run Vellum locally with your own Anthropic API key at no cost beyond your API usage. Vellum also offers a managed mode where you sign in with a Vellum account and the assistant runs on our platform.

What platforms does it support?

The desktop app runs on macOS (Apple Silicon and Intel). There's also an iOS companion app that pairs with your Mac via QR code. Beyond the apps, you can reach your assistant through Telegram, Slack, WhatsApp, phone calls, email, and a command-line interface.

Can I use it on my phone?

Yes. The iOS app connects to your assistant via QR code pairing with your Mac. You get the same chat experience, same personality, same memory. The main limitation is no computer use (iOS doesn't allow accessibility API access). You can also reach your assistant through Telegram, WhatsApp, or phone calls from any device.

About privacy and data

Is my data safe?

Your workspace, memories, and credentials are stored locally on your machine. Credentials are kept in the macOS Keychain or an AES-256-GCM encrypted file, isolated behind a separate Credential Execution Service. However, your conversations and context are sent to the AI model provider (Anthropic) to generate responses. That's the trade-off we're transparent about. Full details in Privacy & Data.

Does Vellum train on my data?

No. From our side, your data is not used for training or fine-tuning. Anthropic's API terms also state that API data is not used for model training. We recommend reading Anthropic's Privacy Policy directly for the most current details.

Does Vellum collect telemetry?

Only if you opt in. There are two optional toggles in Settings > Privacy: usage analytics (anonymized token counts and feature adoption — no message content) and crash diagnostics (error reports via Sentry — no personal data). Both are off by default.

Can my employer see what I do with Vellum?

Vellum runs locally on your machine. We don't have a dashboard, an admin panel, or any way to see your usage. Your workspace is a folder on your hard drive. That said, if your employer monitors your network traffic or your machine, they could potentially see the API calls to Anthropic. Use your judgment based on your work environment.

What happens if I delete the app?

Your workspace folder (~/.vellum/) remains on your machine unless you delete it manually. If you want a clean removal, delete the app and the workspace folder. You can also run vellum retire from the CLI to archive your workspace as a tarball before removing it. See Security Best Practices for the full reset process.

Can other people access my assistant?

Yes, in a controlled way. You can grant trusted contacts limited access to your assistant through channels like Telegram, Slack, or WhatsApp. Trusted contacts can chat with your assistant but can't access your memories, modify your workspace, or use sensitive tools without your explicit approval. Unverified people who message your assistant get heavily restricted access. See The Permissions Model for details on how trust gating works.

About capabilities

What can it do?

A lot. Gmail management, Google Calendar, Slack integration, web browsing, computer control, phone calls, image generation, coding, app building, document writing, task management, screen watching, media processing, and more — about 30 built-in skills in total. You can also build custom skills to extend it further. See the Skills Reference for details on each capability.

Can it access my files?

Files inside the workspace (~/.vellum/workspace/) are accessible without prompts. Files outside the workspace — on your host machine — require your explicit permission each time. You see what file it wants to access, whether it's a read or write, and can choose to allow once, allow temporarily, or create a persistent rule. See The Permissions Model.

Can it send emails as me?

With the Gmail skill, your assistant can draft and send emails from your Gmail account, but sending always requires your explicit approval. It creates a draft first, and you approve before anything is sent. Your assistant can also use its own email address through AgentMail for sending on its own behalf.

Can it control my computer?

Yes, with your permission. The Computer Use skill lets your assistant see your screen (via accessibility APIs and screenshots) and control mouse and keyboard input. This requires macOS Accessibility and Screen Recording permissions, and each action is prompted individually for approval. Sessions are capped at 50 steps with loop detection and destructive action blocking. See Computer Use.

Can I teach it new things?

Yes, in three ways. You can tell it facts and preferences naturally in conversation (it extracts and saves them to long-term memory automatically). You can edit its workspace files directly (SOUL.md for behavior, USER.md for facts about you). And you can build custom skills that give it entirely new tools and capabilities. See Skills & Tools.

Can I use it offline?

No. Your workspace and tools are local, but your assistant needs an internet connection to think — it sends your messages to the AI model provider (Anthropic) to generate responses. Without internet, it can't respond.

About the assistant itself

Can I change its name?

Yes. Say “I want to rename you to [name]” or edit IDENTITY.md directly in ~/.vellum/workspace/.

Can I change its personality?

Yes. Tell it what you want (“be more casual,” “stop being sarcastic”) and it will update SOUL.md. You can also edit SOUL.md directly. Changes to workspace files take effect on the next conversation. See The Workspace.

Can I change how it looks?

Yes. Your assistant has a customizable avatar. Say “put on a wizard hat” or “change your color to emerald” and it will update its appearance. Avatar customization is managed through the assistant's identity and style settings.

What AI model does it use?

Anthropic's Claude by default. The model can be changed in config.json in your workspace.

Does it have feelings?

No. It's very good at sounding like it does, though. Don't let the personality fool you. It's a language model with a good costume.