Source: https://seerepo.com/r/datalab-to/marker/built
Markdown source: https://seerepo.com/r/datalab-to/marker/built.md
Description: marker is a Python repo. It uses AI through surya-ocr, transformers, scikit-learn, torch, OpenAI, and 1 more and connects to Google.

# What is marker built with?

marker is a Python repo. It uses AI through surya-ocr, transformers, scikit-learn, torch, OpenAI, and 1 more, connects to Google, makes its content with pillow, markdown2, filetype, and markdownify, validates its data with Pydantic, and deploys with psutil. It has 16,474 written lines, with 36 test files.

Read on November 6, 2026, at commit 71dd5fd.

Repository: https://github.com/datalab-to/marker

## Backend

### AI

- **surya-ocr**
- **[transformers](https://seerepo.com/uses/transformers)**
- **[scikit-learn](https://seerepo.com/uses/scikit-learn)**: 1 file
- **[torch](https://seerepo.com/uses/torch)**: 1 file

### Services

- **[OpenAI](https://seerepo.com/uses/openai)**: 3 files · [marker/services/azure_openai.py, line 7](https://github.com/datalab-to/marker/blob/71dd5fd7e51ab24f8624b6ba2fcb6014b4e40ed4/marker/services/azure_openai.py#L7)
- **[Google](https://seerepo.com/uses/google)**: 2 files · [marker/services/gemini.py, line 1](https://github.com/datalab-to/marker/blob/71dd5fd7e51ab24f8624b6ba2fcb6014b4e40ed4/marker/services/gemini.py#L1)
- **[Anthropic](https://seerepo.com/uses/anthropic)**: 1 file · [marker/services/claude.py, line 6](https://github.com/datalab-to/marker/blob/71dd5fd7e51ab24f8624b6ba2fcb6014b4e40ed4/marker/services/claude.py#L6)

## Support

### Content

- **[pillow](https://seerepo.com/uses/pillow)**: 22 files
- **markdown2**: 2 files
- **filetype**: 1 file
- **[markdownify](https://seerepo.com/uses/markdownify)**: 1 file

### Validation

- **[Pydantic](https://seerepo.com/uses/pydantic)**: 35 files

### Deploy

- **[psutil](https://seerepo.com/uses/psutil)**: 1 file

### Tools

- **click**: 2 files

### Other

- **tqdm**: 6 files
- **regex**: 3 files
- **ftfy**: 2 files
- **pydantic-settings**: 1 file
- **python-dotenv**: 1 file
- **rapidfuzz**: 1 file

## Other repos with a similar stack

- [run-llama/llama_index](https://seerepo.com/r/run-llama/llama_index/built): OpenAI, Google, transformers, scikit-learn, torch, pillow, filetype, markdownify, Pydantic, psutil · [Compare](https://seerepo.com/compare/datalab-to/marker/vs/run-llama/llama_index)
- [bojieli/ai-agent-book](https://seerepo.com/r/bojieli/ai-agent-book/built): OpenAI, Google, Anthropic, transformers, scikit-learn, torch, pillow, Pydantic, psutil · [Compare](https://seerepo.com/compare/bojieli/ai-agent-book/vs/datalab-to/marker)
- [Aider-AI/aider](https://seerepo.com/r/Aider-AI/aider/built): OpenAI, Google, transformers, scikit-learn, torch, pillow, filetype, Pydantic, psutil · [Compare](https://seerepo.com/compare/Aider-AI/aider/vs/datalab-to/marker)
- [khoj-ai/khoj](https://seerepo.com/r/khoj-ai/khoj/built): OpenAI, Google, Anthropic, transformers, torch, pillow, markdownify, Pydantic, psutil · [Compare](https://seerepo.com/compare/datalab-to/marker/vs/khoj-ai/khoj)
- [browser-use/browser-use](https://seerepo.com/r/browser-use/browser-use/built): OpenAI, Google, Anthropic, pillow, markdownify, Pydantic, psutil · [Compare](https://seerepo.com/compare/browser-use/browser-use/vs/datalab-to/marker)
- [unslothai/unsloth](https://seerepo.com/r/unslothai/unsloth/built): OpenAI, transformers, scikit-learn, torch, pillow, Pydantic, psutil · [Compare](https://seerepo.com/compare/datalab-to/marker/vs/unslothai/unsloth)

## Frequently asked questions

### What language is marker written in?

marker is written in Python, with 16,474 written lines.

### Does marker use AI?

Yes. marker uses AI through surya-ocr, transformers, scikit-learn, torch, OpenAI, and Anthropic.

### What services does marker use?

marker connects to Google.

The proof: [marker/services/gemini.py, line 1](https://github.com/datalab-to/marker/blob/71dd5fd7e51ab24f8624b6ba2fcb6014b4e40ed4/marker/services/gemini.py#L1)

### Does marker have tests?

Yes. marker has 36 test files.

### Which repos have a stack like marker's?

The ones that share most of its stack: run-llama/llama_index, bojieli/ai-agent-book, and Aider-AI/aider.

## 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.
