Modelbit

Name: Modelbit
Rating: 5.0 (2 reviews)

Heroku for Data Science, from the founders of Periscope Data

5.0•2 reviews•

102 followers

Heroku for Data Science, from the founders of Periscope Data

5.0•2 reviews•

102 followers

Visit website

Run `modelbit.deploy()` from your Jupyter Notebook to deploy your ML model to production. Automatically get REST and Snowflake inference endpoints. Version control, CI/CD, logging, containerization, pipelines and feature stores come built-in.

Free Options

Launch tags:Developer Tools•Artificial Intelligence•Data Science

Launch Team

Framer AI AgentsDesign and publish professional sites with AI

Promoted

Modelbit

Maker

📌

👋 Hey makers! My best friend Tom and I have spent our careers making data tools together. After spending the last decade building Periscope Data, we're launching our next project, Modelbit! 🚀 Modelbit is a labor of love after a decade spent watching data scientists struggle to deploy models. The data scientists at Big Tech companies get whole teams of ML Engineers to help them deploy. Everyone else is out of luck ... until now! From any Python notebook, just run `modelbit.deploy()`. From there, a whole bunch of cool stuff happens under the hood: 👉 Detect and containerize the running Python environment 👉 Ship the model and its container to the cloud 👉 Give the model a REST endpoint and Snowflake SQL function for inference 👉 Version control the model in your git repo 👉 Scaffold load balancing, logging, unit testing and more 👉 Stand up retraining pipelines, A/B testing, and feature stores in case you want them! We love data teams and we're proud of the work we do supporting and enabling them. We hope you'll find this latest project useful. ❤️

Report

3yr ago

Product Hunt

I already have a bit of context about Modelbit (we invested at Weekend Fund) but I'm curious to ask a questions somewhat unrelated to this launch... @harry_glaser – You and Tom previously built and exited Periscope Data for over $100M. You know how hard it is to build a large company. Why do it again? Isn't it easier to just rest and vest at a large co. 😅

Report

3yr ago

Modelbit

Maker

@rrhoover The short answer is @tom_o_neill wanted to go again. Who was I to say no? 🤣 Truly, we love it. Data teams are such a fun group to build for. There's nothing like a smart, positive, kind community of users. I don't think there's a better way to spend your career than building data tools with your best friend.

Report

3yr ago

The Breaking Point Newsletter

After building many ML centric products over the years, I can attest that getting a model into production is one of the hardest problems in software. It's so hard that it often slows down product development to a crawl, as the Data Scientists don't have the skills to move a model into production but the engineers don't understand how the models work. ModelBit is addressing this head on and I wish we had it when I was still building products!

Report

3yr ago

We've been Modelbit users for a while now and love the product and the team. Here's an example of what we've built: https://medium.com/building-inve...

Report

3yr ago

Very glad to work with you guys! Being able to get the support we need, almost real-time, and push some of the complexity of ML deploying to you (sorry, not sorry) unblocks our model building/deployment by a LOT. 😁

Report

3yr ago

The experience for data scientists is amazing (permissionless starts, one-line deploys, etc). I love the “creativity loves constraints” philosophy you’ve adopted that rules out the massive adoption, usage, and maintenance headaches associated with heavy-duty ML platforms.

Report

3yr ago

Congratulations on the launch of Modelbit, your new project! As experienced makers of data tools, it's inspiring to see your decade-long commitment in this field, starting from Periscope Data and now venturing into Modelbit. The struggle faced by data scientists when deploying models has been acknowledged, and Modelbit aims to provide a solution. With just a single command, modelbit.deploy(), Modelbit simplifies the deployment process from any Python notebook. It offers a wide range of functionalities, such as containerizing the running Python environment, shipping models and containers to the cloud, and providing REST endpoints and Snowflake SQL functions for inference. Version control in Git repositories, load balancing, logging, unit testing, retraining pipelines, A/B testing, and feature stores are also incorporated. Your dedication to supporting data teams is evident, and Modelbit is poised to be an invaluable resource for data scientists. Congratulations once again on this remarkable achievement, and we wish you great success with Modelbit!

Report

3yr ago

1 2

5.0

Based on 2 reviews

Review Modelbit?

Reviews

Most Informative