Independent researcher and music teacher based in Portugal. I've spent the last year developing the Fresta Lens Framework — a 5-volume (~500 pages) theoretic
| Machine Learning | 42 |
|---|---|
| Computer Vision | 0 |
| Data Science | 25 |
| NLP & LLMs | 66 |
| AI Agents | 58 |
| MLOps | 21 |
Each node is one domain, scored only from evidence in these public repositories. Select one to see why.
Deep, repeated, well-engineered work in this domain.
2 of 3 public repositories contain AI work and are included in this Atlas. The remaining 1 (repositories without AI code, forks and empty repositories) are excluded from scoring 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.
68% of Atlas Score
Fresta Diamond is a Python runtime library that provides typed contracts, persistent state management, and explicit effect controls for LLM-based applications, featuring module admission, attention continuation, and cognitive architecture concepts.
32% of Atlas Score
FRSTA-EDGE is a Python script that generates domain-specific evaluation lenses using a three-order structural analysis framework, leveraging Wikipedia/web scraping and a local LLM to produce weighted metrics, interdependency maps, systemic stress factors, and buyer profiles.
