only have spirit.
| Machine Learning | 60 |
|---|---|
| Computer Vision | 0 |
| Data Science | 49 |
| NLP & LLMs | 64 |
| AI Agents | 0 |
| MLOps | 29 |
Each node is one domain, scored only from evidence in these public repositories. Select one to see why.
Substantial implementations with real depth.
50 public repositories → 5 with AI work, evaluated. The other 45 (repositories without AI code, forks and empty repositories) are not scored and have no effect on the result. How repositories are selected
Ordered by how much each project adds to the Atlas score, not by its own score. A project with evidence in several domains can rank above one with a slightly higher project score. Choose a domain to focus on the projects with meaningful evidence there.
45% of Atlas Score
The repository is a full-stack application that generates evidence-grounded multiple-choice quiz questions from user-uploaded documents using a retrieval-augmented generation pipeline with a novel Cross-CoVe verification step involving multiple LLM reviewers.
22% of Atlas Score
A FastAPI-based retrieval-augmented generation system for creating medical multiple-choice questions, featuring hybrid BM25 and MedCPT retrieval, LLM-based question generation, and multi-faceted LLM verification.
17% of Atlas Score
CacaoID is a full-stack web application that verifies cocoa seed genetics using SNP data and provides machine learning-based trait predictions for breeding decisions.
15% of Atlas Score
Skor Risiko is a self-hosted Telegram bot that assesses the risk of Indonesian stocks using 28 rule-based indicators and explains the results in plain Indonesian via an LLM, with a number gate to ensure factuality. It features automated alerts, data caching, and a containerized deployment for ease of use.
The repository is a Flutter project containing standard Windows runner code and a minimal README. The main application logic (in Dart) was not provided for evaluation.
