Warehouse every AI request to your database. Query logs to analyze usage and costs, evaluate models, and generate datasets. Install the proxy with 2 lines of code. It’s free to get started, and you own your data.
Hey Product Hunt 👋 Emma and Chris here from Velvet. We built an AI gateway to warehouse OpenAI and Anthropic requests to your database. Engineers use Velvet logs to analyze usage and costs, evaluate models, and generate datasets.
Our first product was an AI SQL editor. It worked really well, but we had limited insights into what happened between our app and OpenAI. We started storing requests to our database, giving us the ability to query data directly. It gave us so much more control over developing our AI features.
We didn’t think of it as a product until one of our customers (Find AI) asked to use it. We warehoused over 3 million requests for them in the first week, logging up to 1,500 requests per second during their launch. Now we have many startups using Velvet daily for caching, evaluations, and analysis of opaque endpoints like the Batch API.
It's easy to get started! Once set up, we warehouse every request to your database.
Requests are formatted as JSON. You can include custom metadata in the header - like user ID, org ID, model ID, and version ID. This means you can run complex SQL queries unique to your app. Granularly calculate costs, evaluate new models, or identify datasets for fine-tuning.
We'd love to hear from you! Email [email protected] with any feedback or questions.
Hey Emma and Chris congrats on your new product launch!
Velvet is really amazing product. we can Warehouse every AI request to your database. Query logs to analyze usage and costs, evaluate models, and generate datasets. we can also Install the proxy with 2 lines of code. It’s free to get started, and we own your data.
If you’re looking to amplify your reach and make an impact, BlogHunch can be your go-to content marketing platform. You can create engaging blogs, send targeted newsletters, and even sell digital products—all from one place.
Why BlogHunch?
AI-powered blogging for seamless content creation.
Newsletter automation to keep your audience engaged.
Easy digital product selling to boost your revenue.
Let us handle your marketing while you focus on building great products! :muscle: Ready to give it a try? Check us out: bloghunch.com
The Velvet team is stellar--I've been watching them constantly improve the product for the better part of a year by eliciting and responding (swiftly) to feedback.
This tool is a must-have for anyone working with AI. Being able to warehouse and query AI requests in a centralized database is incredibly valuable for understanding usage patterns, optimizing costs, and improving model performance. Congratulations on the launch!
I noticed the demo video link seems to be broken . It would be great to see it working to get a full picture of Velvet’s capabilities.
Congrats on the launch! Making our LLM requests actually queryable has been on our wishlist and isn't quite satisfied by logging/observability providers we know about. Excited to test it out 🔥
👏 Congrats on the launch! This product is a game-changer, and I can't wait to start using it. You're amazing! 💪
@emmalawler24
The caching feature might really help in lowering the costs and improving response time
Concept is so intersting like logging and analyzing AI requests directly from my app sounds practical
I can vouch for Emma and Velvet. I was one of the early users and have enjoyed the product mindset the team has, I am excited about this pivot. Good Luck.
Congrats on the launch @emmalawler24 !! As a user of Velvet, I can't think of a better tool for us to monitor LLM usage.
Does this tool support integration with other data analysis platforms or BI tools? Also, how does it handle data privacy and security?
Hi! The concept of warehousing AI requests and analyzing them sounds like a great way to gain deeper insights into AI usage and costs. The ease of installation with just 2 lines of code is a huge plus.
Great work! I'm really impressed by the ability to track usage and costs, evaluate models, and generate datasets could be incredibly useful for optimizing AI workflows.
Using this tool has made managing AI logs so much easier. The caching feature is a big plus for cutting costs.
