Monthly | Top 10 GitHub Repos | October 2025

Noteworthy data-ops & analytics repos that first shipped between one and three years ago.

Oct 01, 2025

#10. Cinnamon/kotaemon

An open-source RAG-based tool for chatting with your documents.

[”chatbot”, “llms”, “open-source”, “rag”]

This repo was first pushed to Github on 2024-04-03. Its license was listed as: Apache License 2.0. Its primary language is Python.

#9. adithya-s-k/omniparse

This repo was first pushed to Github on 2024-06-10. Its license was listed as: Apache License 2.0. Its primary language is Mixed/Unspecified.

#8. z1069614715/objectdetection_script

一些关于目标检测的脚本的改进思路代码，详细请看readme.md

This repo was first pushed to Github on 2023-01-05. Its primary language is Python.

#7. Azure-Samples/azure-search-openai-demo

A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.

["azure","azurecognitivesearch","chatgpt","openai","azureopenai","azd-templates"]

This repo was first pushed to Github on 2023-03-09. Its license was listed as: MIT License. Its primary language is Python.

#6. weaviate/Verba

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

This repo was first pushed to Github on 2023-07-28. Its license was listed as: BSD 3-Clause "New" or "Revised" License. Its primary language is Python.

#5. facebookresearch/nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

This repo was first pushed to Github on 2023-08-28. Its license was listed as: MIT License. Its primary language is Python.

#4. chidiwilliams/buzz

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.

["whisper"]

This repo was first pushed to Github on 2022-09-24. Its license was listed as: MIT License. Its primary language is Python.

#3. openai/tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

This repo was first pushed to Github on 2022-12-15. Its license was listed as: MIT License. Its primary language is Python.

#2. Byaidu/PDFMathTranslate

Latex PDF 翻译及双语对照，保留公式和图表排版

["chinese", "latex", "pdf", "translation"]

This repo was first pushed to Github on 2024-09-06. Its license was listed as: MIT License. Its primary language is Python.

#1. drawdb-io/drawdb

Free, simple, and intuitive online database design tool and SQL generator.

This repo was first pushed to Github on 2024-04-06. Its license was listed as: MIT License. Its primary language is JavaScript.