Product Roadmap

Talk to your assistant out loud, interrupt it, and have it talk back — with low enough latency that it feels like a real conversation.

Your assistant doesn't go dark when your laptop closes. Move seamlessly between local and cloud — same memory, same identity, same conversations.

Your assistant delegates to specialized helpers in parallel — research, coding, writing — and brings the results back to you.

I want my assistant to join my calls to take notes and have the context of the things Im working on. Ideally it can start tasks discussed in meetings before I tell my assistant to get on them lol.

Wire any service into your assistant with a simple webhook. If it can POST, your assistant can react to it.

A native Apple-ecosystem channel for your assistant — texts, read receipts, the works.

Vellum for android,vscode,windows Android supports press the power button to call agent

Your assistant notices when it got something wrong and quietly gets better at it. No fine-tuning pipeline required.

Your assistant adapts to how you work — tone, habits, preferences, the people you talk to. It gets more yours the longer you use it.

I would really really like mobile/web support for locally hosted. through the vellum account. please!

Summon your assistant inside any app on your system — summarize a doc, reply to a message, translate a selection — without switching windows.

Your assistant can talk to other assistants — coordinating schedules, sharing context, negotiating on your behalf.

I love the product, but it’s quite laggy and glitchy. And I love the roadmap ideas, but stability is king!

Would love to see the Vellum assistant available as a self-hosted option on Linux. Currently the assistant is macOS-only for local hosting, which locks out a large portion of developers and power users who run Linux as their primary OS or on home servers. Use cases include: runni…

Have my assistant write and read discord messages and act as a member of a community.

Make your assistant look and feel the way you want it to. Themes, avatars, and the small cosmetic details that make something feel like yours.

The small recurring stuff — birthdays, renewals, reservations, errands — handled without a spreadsheet.

Pull signals from the wearables you already have and turn them into useful nudges, not a dashboard you have to check.

A community hub for teaching your assistant new tricks. Pull in skills others have built; publish your own.

One assistant that coordinates multiple coding agents across your repos — planning, delegating, and shipping end-to-end.

A work assistant and a personal assistant. Or one per project. Separate memories, separate identities, same you.

Choose your own color for your assistant instead of the preset ones only

I think it will be way better if i could set a maximum amount of automatic retries for a model, provider or a profile before it shows an error, or choose a fallback model for an another model. I hate when i give my agent a task, walk away, and when i come back i just get disappoi…

I want the web app to restore app state from IndexedDB on startup, then sync with the server/SSE in the background as needed. Right now it looks like only smaller UI state is persisted locally, while the main app state is rebuilt on refresh.

What you're trying to do Use the assistant over Telegram and get real clarifying questions when it’s unsure — pick an option (or type a short answer) in the chat, then continue the turn. Same outcome as the choice card in web/macOS, just on Telegram. What you tried or where you…