XetHub for

Generative AI

XetHub is the best platform for developing Generative AI apps. Build full apps by yourself. Deployment is coming soon!
Join us for an upcoming Virtual Workshop, "MyGPT: Build a ChatGPT For Your Own Data in One Hour"

Organize it all

XetHub makes it easy to track the dataset, code, models, embeddings, prompts, and more - all in one place.

  • One standard Git repository to track everything.
  • Use branches to track experiments and try out prompts.
  • Streamline deployment using Git today, and using XetHub coming soon (join our Discord to find out more)!
  • Being on the bleeding edge requires keeping track of all the moving parts (all the packages involved are changing daily) so version control becomes essential.

We rely on computer vision and ML to deliver on Gather AI’s mission. XetHub has enabled our ML team to be more productive, collaborate efficiently, and iterate quickly.”

Daniel Maturana, Co-Founder and Chief ML Scientist


reduction in repository size and transfer time


data silos eliminated by switching to XetHub


cost savings over using EBS, Git LFS, and DVC

Stay in the flow with Python

  • Open-source Python package (https://github.com/xetdata/pyxet)
  • Full support for Python fsspec and Pathlib
  • Natively integrates with Pandas, Pyarrow, Dask, Polar.rs, DuckDB, and more
  • All of the convenience of a blob store, with tracking built-in.
  • Launch a Jupyter Notebook from within XetHub, save edits as commits back to repository. (coming soon!)

Experiment freely with efficient deduplication

  • Block-level deduplication results in significant savings
  • Each version of the embeddings (vector db) is easily GBs, though most of it is duplicated across versions.
  • Example screenshot for demo Gen AI application. 15GB on disk, stored in 4.4GB. For the latest version it is 1.8GB on disk. Fork it and try for yourself!
  • Leverage branches, forks, and pull requests to have full flexibility, without sacrificing tracking & history.

Deployment is handled: Share with the world

  • Streamline deployment with Git today - the latest model is just a Git pull away
  • One-click deployment of a Gradio or Streamlit application directly from XetHub repository (coming soon!)
  • Share deployed app via URL to anyone for public repositories, enable forking the app for their own customization. (coming soon!)
  • Privately share your app using standard XetHub permissions (Viewers, Writers, Maintainers) of your repository. (coming soon!)
XetHub logo with white text

Delightful collaboration on code and data at any scale.

Copyright current year XetData