Senior Software Architect & Builder | Creator of LinguaArush.com & open-source Python packages (compareexcel on PyPI) | C#, .NET Core, Python & JS.
| Machine Learning | 47 |
|---|---|
| Computer Vision | 0 |
| Data Science | 16 |
| NLP & LLMs | 53 |
| AI Agents | 55 |
| MLOps | 9 |
Each node is one domain, scored only from evidence in these public repositories. Select one to see why.
Substantial implementations with real depth.
30 public repositories → 2 with AI work, evaluated. The other 28 (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.
65% of Atlas Score
TrailGuideRAG is a local retrieval-augmented generation (RAG) system for outdoor-skills activities. It ingests Markdown documents, creates embeddings with Sentence Transformers, stores them in Chroma, and uses a local Hugging Face instruct model to generate grounded answers with citations.
35% of Atlas Score
WeatherAgent is a rule-based agent system that orchestrates geocoding and weather APIs to provide outdoor activity recommendations based on natural language user queries. It implements a session-based conversation flow with tool usage for location resolution, date parsing, and weather risk evaluation.
