VIEW AS:

Vellum vs Gumball

Gumloop logo

Gumball

  • Native Daily Chew morning catch-up digests and automated pre-meeting briefs
  • Deep integration with Gumloop's no-code workflow canvas and team-shared skills
  • Smart Inbox automated categorization and draft replies for Gmail and Outlook
  • Cloud-native background monitoring across 100+ business connectors and MCP integrations
Vellum logo

Vellum Assistant

  • Model agnostic: Use any frontier AI model, open or proprietary, and switch anytime.
  • Truly yours: Give it a name and personality. It learns you, your work, and your tools.
  • Self-improving: Gets better the more you use it, with one memory across every device.
  • Private by design: Credentials stay secure, and you choose where your data lives, including self-hosting.
  • Built for busy business owners: Offload work and make more time for life.
Available on Web, macOS, iOS, Android & Windows
Vellum assistant on desktop and mobile

Which one is right for you?

Gumball is Gumloop's cloud sidekick for workplace operations, automating morning digests, meeting prep, and inbox triage across corporate SaaS tools. It ties directly into team automation canvases, with your data, memory, and execution metered by monthly cloud credits.

Vellum handles those same workplace briefs, schedules, and daily tasks, but lives on your computer with complete data ownership. You get an autonomous personal assistant out of the box with zero technical setup, continuous memory across your devices, and your private data never trapped in a closed cloud.

Which setup fits you best?

Gumball operates across the Gumloop web application, Slack direct messages, and dedicated email threads, connecting directly to cloud SaaS APIs and automated workflows.

Vellum lives where you work: a native Mac app that controls your local computer, mobile apps on iOS and Android, web app, voice calling, email, Slack, Telegram, and terminal, all connected to one persistent assistant.

Vellum available on multiple platforms
Four shields representing data privacy and protection

How do you want privacy and security handled?

Gumball processes data in Gumloop's multi-tenant cloud with role-based admin controls, reserving private VPC deployments for Enterprise contract customers.

Vellum gives you complete architectural ownership: run locally on your physical device with zero cloud transmission, self-host under MIT, or use Vellum Cloud with isolated credential vaults that keep your keys and passwords private.

Compare assistants side by side

Channels
Vellum

iOS app with Home Screen widgets, native Mac app, web app, voice, email, Slack, Telegram, Microsoft Teams, and Discord, now an official channel with a setup wizard. Sent messages can be edited in place in Slack and Telegram. Every surface shares the same memory and identity.

Gumball

Direct messages in Slack, dedicated gumball@gumloop.ai email address, and web dashboard.

Execution
Vellum

Build me a habit tracker gets you a working, interactive app in the conversation. Read this page uses the browser extension to read your open tabs and act on the page you are looking at. Call the dentist and reschedule places an actual phone call with its own voice.

Gumball

Executes API calls, web scraping, and Python scripts across distributed cloud workers.

Hosting
Vellum

Run on-device as a native Mac app, on Vellum's managed cloud, or self-host on your own VPS.

Gumball

Runs on Gumloop cloud workers with scheduled background triggers; no local hosting.

Integrations
Vellum

Native agent skills plus 1-click integrations with 50+ services through managed OAuth, including native Calendly and Eventbrite. Your assistant acts in real services without you touching tokens or API keys.

Gumball

Extensive pre-built connectors for Gmail, Outlook, Slack, Salesforce, HubSpot, Linear, and MCP servers.

Memory
Vellum

Vellum builds a structured memory of your projects, people, and preferences automatically, across every surface. It sharpens with every conversation and correction, and there is nothing to configure: no files to curate, no engine to pick, no embedding provider to wire up.

Gumball

Tracks personalized tone and design rules, situational highlights, and past run feedback in cloud storage.

Modularity
Vellum

Builds its own skills, learns your tone, and adapts based on what you reward and correct. Install new skills from a growing library, or just ask and it figures out a way.

Gumball

Extensible visual node canvas, reusable SKILL.md imports, and multi-agent delegation.

Open Source
Vellum

Open source under MIT license. Full codebase available on GitHub.

Gumball

Proprietary cloud platform with closed-source engine, web builder, and orchestration harness.

Pricing
Vellum

Free Base plan with free credits to start. Paid plans from $30/mo (Mighty), $100 (Super), and $200 (Ultra) with pay-as-you-go credits, configurable compute and storage, and your assistant's own email and subdomain on higher tiers.

Gumball

14-day free trial, Pro plan from $37 per month on a credit slider, and custom Enterprise contracts.

Privacy
Vellum

Run locally on Mac, in Vellum Cloud, or self-host. Vellum never has access to your data on any deployment path.

Gumball

Processes data across Gumloop cloud infrastructure, with dedicated VPC options on Enterprise contracts.

Schedules
Vellum

Built-in scheduling for daily briefings, weekly reports, and hourly checks that just run on a cadence.

Gumball

Automated morning briefings, pre-meeting triggers, and custom interval schedules.

Security
Vellum

Credentials live in an isolated vault and never enter the model layer, so prompt injection can't exfiltrate your keys. Every sensitive action asks permission with a risk badge before it runs, and guardian approvals land in one inbox.

Gumball

Admin-governed connector controls, role-based skill permissions, and credit rate limits.

Setup
Vellum

No terminal, no API keys, no daemon. Voice-first onboarding is the default: your first experience is speaking, not configuring. Free, no credit card, up in minutes.

Gumball

Auto-created on account signup; connects to workplace apps via standard browser OAuth.

Storage
Vellum

Vellum Cloud: 3 GB RAM and 4 GB storage by default. Mac app runs on standard Mac hardware.

Gumball

Stores generated artifacts, interactive apps, and company brain documents in Gumloop cloud.

Trust
Vellum

Every sensitive action asks first with a risk badge, guardian approvals land in one inbox, and you can export or delete your data at any time. The trust model is written down in the docs.

Gumball

Interactive Needs Work feedback in Slack and step-by-step plan reviews before agent execution.

Compare all AI assistants

See how every personal AI assistant stacks up across the categories that matter.

Frequently asked questions

Should I choose Vellum or Gumball for a personal AI assistant?

Choose Vellum if you want an autonomous personal assistant for daily work, errands, and private projects with full data sovereignty, free cloud hosting, and continuous memory that lives on your Mac, phone, and messaging apps. Choose Gumball if your primary goal is automating team SaaS workflows inside Slack, email, and Gumloop's visual automation canvas.

When does Gumball make more sense than Vellum?

Gumball makes sense if your team already relies on Gumloop for visual workflow automation and you want a shared AI sidekick that handles morning inbox triage, pre-meeting briefs, and connector-driven tasks inside your corporate Slack workspace. If you want a personal assistant that manages your local files, runs natively on your computer, and keeps your private context independent from corporate cloud meters, Vellum is built for you.

How much does Vellum cost compared with Gumball?

Vellum includes free cloud hosting when you sign up. Paid plans upgrade compute and storage: Mighty at $30 per month, Super at $100 per month plus a $10 platform fee, Ultra at $200 per month plus a $10 platform fee, and Custom. Self-hosting has no platform fee. Gumloop offers a 14-day free trial, with paid Pro plans starting at $37 per month for 20,000 credits on a usage slider, scaling up to custom Enterprise contracts.

How does Gumball's security compare to Vellum's credential vault?

Gumball secures credentials in Gumloop's cloud repository with role-based admin controls and optional VPC deployment for Enterprise clients. Vellum isolates credentials in a dedicated local or cloud execution vault where passwords and API keys never enter the prompt context, while keeping the entire assistant architecture open-source and auditable.

Can I self-host Gumball or run it on my own computer?

No. Gumball runs exclusively on Gumloop's managed cloud infrastructure, with private VPC deployment available only for Enterprise contract customers. Vellum can run directly on your own computer as a native Mac app with local memory, self-hosted on your private server under the MIT license, or deployed in managed Vellum Cloud.

Can Vellum brief me on meetings and summarize my inbox like Gumball?

Yes. Vellum connects to your Google Calendar, Outlook, and email accounts to deliver morning briefings, summarize incoming messages, draft replies in your personal tone, and prepare agenda briefs before upcoming meetings, all while keeping your data under your own control.

What messaging apps do Vellum and Gumball support?

Gumball supports direct messaging inside Slack, a dedicated gumball@gumloop.ai email address, and the Gumloop web application. Vellum connects across Mac, iOS, Android, web app, voice calling, email, Telegram, Slack, and terminal, sharing continuous memory across all surfaces.

Where does my data live with Gumball vs Vellum?

With Gumball, all prompt history, connector tokens, generated artifacts, and meeting notes are stored in Gumloop's cloud database. With Vellum, you choose your data residency: keep your memory entirely local on your physical Mac, self-host on your own infrastructure, or use managed Vellum Cloud with isolated credential vaults.

Can I use models like Claude, GPT, or local models with Gumball?

Gumball automatically selects models based on task complexity from the models permitted by your organization. Vellum gives you explicit multi-model routing control, letting you select Anthropic Claude, OpenAI, Google Gemini, OpenRouter, or private local models running offline via Ollama.

Can Gumball manage files on my physical laptop?

No. Gumball operates strictly across cloud SaaS APIs and web connectors. It cannot directly read, edit, or organize files on your personal physical computer. Vellum runs natively on your machine, managing local folders, running terminal commands, and coordinating desktop workflows directly.

Is Vellum or Gumball easier to use for non-technical users?

Both provide zero-friction onboarding. Gumball is ready on signup via web and Slack, while Vellum provides a complete personal assistant across Mac, phone, web, voice, email, and messaging with no server configuration needed. The difference is architectural: Gumball is a cloud automation teammate metered by credits, while Vellum is your personal assistant that you own.

Make a personal assistant in your image

Get Started →