Source: https://seerepo.com/r/xorbitsai/inference
Markdown source: https://seerepo.com/r/xorbitsai/inference.md
Description: xorbitsai/inference is a Python repo with 922,374 lines written. AI signed 0.3% of the 2,791 commits of inference.

# What's inside xorbitsai/inference

xorbitsai/inference is a Python repo with 922,374 lines written. inference is built with FastAPI, Lightning, uvicorn, and 4 more and uses Hugging Face and OpenAI. AI signed 0.3% of the 2,791 commits of inference.

Its description on GitHub: “Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.”

Python · Apache-2.0 · 9,655 stars · GitHub: https://github.com/xorbitsai/inference

Read on November 14, 2026, at commit d2607af.

## More on this repo

- [What is inference built with?](https://seerepo.com/r/xorbitsai/inference/built): inference is built with FastAPI, Lightning, uvicorn, and 4 more and uses Hugging Face and OpenAI.
- [How much of inference did AI write?](https://seerepo.com/r/xorbitsai/inference/ai): AI signed 0.3% of the 2,791 commits of inference.

## In figures

- 922,374 lines written: The ones people and agents wrote: product, tests, schemas and tooling. Generated code doesn’t count.
- 2,727 product files: The product’s own files. Test files are counted apart.
- 676 test files: The files that test the code.
- 87 technologies: Each service with the file and line that prove it.

SeeRepo read the facts in its code and kept none of it. AI only helps sort its packages and folders by their names, and never sees its code.

## Frequently asked questions

### What is xorbitsai/inference?

xorbitsai/inference is a Python repo with 922,374 lines written. Its description on GitHub: “Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.”

The proof: [its page on GitHub](https://github.com/xorbitsai/inference)

### What is inference built with?

inference is built with FastAPI, Lightning, uvicorn, and 4 more and uses Hugging Face and OpenAI.

The proof: [each service with its file and line](https://seerepo.com/r/xorbitsai/inference/built)

### How much of inference did AI write?

AI signed 0.3% of the 2,791 commits of inference.

The proof: [the commits each tool signed](https://seerepo.com/r/xorbitsai/inference/ai)

### What license does inference have?

inference is released under the Apache-2.0 license.

The proof: [its page on GitHub](https://github.com/xorbitsai/inference)

### How many stars does inference have on GitHub?

inference had 9,655 stars on GitHub on November 14, 2026.

The proof: [its page on GitHub](https://github.com/xorbitsai/inference)

## Add this badge to your README

It links to this page and updates itself each time SeeRepo reads the repo.

```markdown
[![xorbitsai/inference on SeeRepo](https://seerepo.com/badge/xorbitsai/inference.svg)](https://seerepo.com/r/xorbitsai/inference?de=insignia)
```

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.