Towards Data Science is a community-powered publication that showcases work in data science, machine learning and artificial intelligence. Every day newcomers, seasoned researchers and industry practitioners publish tutorials, research notes and real-world case studies that help the field move forward.

Towards Data Science

OSA (Open Source Advisor) is an open-source Python tool that uses LLM-powered multi-agent workflows to automatically improve open-source repositories. It generates README files (including article-style READMEs for scientific repos), adds docstrings and MkDocs-based documentation, sets up CI/CD workflows for GitHub and GitLab, and creates contribution guidelines. Users can run it via CLI or a web GUI, choosing from basic, auto, or advanced modes. The tool supports OpenAI, OpenRouter, and local models like Ollama. A real-world example shows a repository's OpenSSF Scorecard rising from 2.2 to 3.7 after OSA processing. Future plans include RAG-based comparison against best-practice repositories and multi-language support.

An End-to-End Guide to Beautifying Your Open-Source Repo with Agentic AI