Product
Vellum
by Vellum
- Product website
- https://www.vellum.ai
- Categories
- No categories listed.
Description
An open-source personal AI assistant available as a native Mac app or in Vellum Cloud.
AI-native score
How ready this product is for agents to use, on a 0–100 scale across four weighted dimensions. Security is one of them, so a high score is not a substitute for your own security or vendor-risk review. How is this scored?
Unrated. Only 4% of the scored decision fields are researched, so the grade is held until more are confirmed. The breakdown below shows what's been scored.
| Component | Raw | Weight | Contribution |
|---|---|---|---|
| Integration | 0/10 | 35% | 0.0 |
| Trust | 2/6 | 30% | 10.0 |
| Portability | 0/4 | 20% | 0.0 |
| Security | 0/4 | 15% | 0.0 |
Signals that fired
- Trust: No generative AI training (yes, +2)
Signals not researched
These gaps cover the fields used in the AI-native score.
- Integration surfaces: llms.txt, WebMCP, Headless signup, MCP servers, Agent2Agent (A2A) servers, Native connectors, API specs, Command-line interfaces, Agent skills, Developer kits
- Trust & data policy: Trust center, Multi-factor authentication, Zero data retention, Hard budget caps, Sandbox environment, Data export, Data import, Open standards, Standard protocol access, No proprietary-SDK lock-in, Documented provider swap, Self-hostable, Open source
- Security & compliance: Compliance certifications, Access controls
Trust & data policy
- No generative AI training
- Yes
Not yet researched Trust center, Multi-factor authentication, Zero data retention, Hard budget caps, Sandbox environment, Data export, Data import, Open standards, Standard protocol access, No proprietary-SDK lock-in, Documented provider swap, Self-hostable, Open source
Offers
No offers recorded.
Reviews
No approved reviews yet.
Catalog activity
Track how this entry changes as proposals are opened and merged.
Ready to decide?
Unrated · 4% researched. Grade withheld until more fields are verified.