vellum-assistant

Personal AI assistant with eight memory types, hourly proactive check-ins and channels from macOS and iOS to Slack and Telegram.

Agent by vellum-ai

IndexedMIT★ 1,449

Write a review

Get started

Setup steps are in the repository. Website · Repository

About

Vellum Assistant keeps eight kinds of memory, writes its own personality files during onboarding, and re-reads its notes every hour to message the user about unfinished or due items. Actor identity is enforced so unknown senders cannot read memory or trigger tools, and every tool call runs in a sandbox. It runs as a managed cloud runtime on Vellum Platform or fully on the user's machine, with apps for macOS and Windows.

Use cases: personal-assistant, agent-memory, scheduling, team-chat

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Jobs: personal assistantREADME
Autonomy: Autonomous: runs tasks end to end and reports backREADME
Where you use it: Desktop app, Mobile, Web, Voice, Email, Slack, otherREADME
Hosting: Hosted or self-hostedREADME
Open source: YesREADME

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Signals

Stars: 1,449
Forks: 216
Open issues: 56
Last commit: Oct 23, 2026 (5 days ago)
Last release: Sep 29, 2026 (29 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/vellum-ai/vellum-assistant
Website: vellum.ai
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql