Ross ROSS = Recommend OSS · open-source software intelligence for agents

vellum-ai/vellum-assistant

An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time. observed · 2026-09-03

github.com/vellum-ai/vellum-assistant · homepage · TypeScript · MIT (permissive) observed · 2026-09-03

Health v2 · maintenance only

79/100

  • Activity 100
  • Release rhythm 88
  • Longevity 14
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 0
  • age_days: 207
  • days_rel: 1
  • days_push: 0
  • n_releases_24m: 148

Full methodology

Adoption not part of the score

1179 stars · 168 forks observed · 2026-09-03

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Vellum is an open-source personal AI assistant that runs 24/7, learns your preferences through eight types of persistent memory, and takes real actions across your apps and channels (macOS, iOS, web, Slack, Telegram, email). It ships with identity/personality files, proactive hourly check-ins, sandboxed tool execution, and OAuth integrations, and can be self-hosted or run on Vellum Cloud.

Use cases

  • set up a personal AI assistant that remembers my preferences
  • AI assistant that works for me 24/7 and messages me proactively
  • self-host an AI agent with persistent long-term memory
  • one AI assistant across Slack, Telegram, email and iOS
  • alternative to building a personal AI on Claude Code or OpenClaw
  • AI assistant that can send emails and manage my calendar
  • assistant with its own identity and email address

When to choose

  • you want an out-of-the-box personal AI assistant instead of assembling one yourself
  • you need rich multi-type memory with local embeddings and per-user isolation
  • you want proactive behavior like reminders and follow-ups across channels
  • you want to self-host on your own hardware with full data control

When to avoid

  • you need a fully local/offline assistant with no cloud dependency
  • you want a simple stateless chatbot without memory or proactivity
  • you require Windows or Linux desktop apps (macOS/iOS/web are the clients)
  • you need strict data residency and can't accept a managed cloud option

Facets

application · maturity active

agent-framework chatbot rag auth webhook scheduling artificial-intelligence large-language-models developer-tools self-hosted self-hosted cross-platform personal-ai-assistant memory-systems proactive-agent openclaw claude-code oauth-integrations multi-channel typescript memory ai-agents automation macos ios web-server telegram discord

8 sources

Member repositories

RepositoryRoleHealth v2
vellum-ai/vellum-assistantmain79

For agents

markdown · JSON · MCP: product_card(name="vellum-ai/vellum-assistant")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem