Anxious, Busy, Curious
AI-Atlas score
| Machine Learning | 62 |
|---|---|
| Computer Vision | 26 |
| Data Science | 47 |
| NLP & LLMs | 63 |
| AI Agents | 56 |
| MLOps | 18 |
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 → 13 with AI work, evaluated. The other 17 (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.
25% of Atlas Score
This repository provides a self-contained C++ implementation of the Byte Pair Encoding (BPE) tokenization algorithm, including a driver program that trains BPE on a text corpus and outputs the merged pairs. A companion Python script automates repeated compilation and execution for demonstration.
17% of Atlas Score
Orion is a personal AI coding agent that provides an interactive CLI for executing prompts, managing tools, and automating software development tasks. It features context management, streaming responses, and Docker support for reproducible deployment.
16% of Atlas Score
This repository implements a Dream11 fantasy cricket team prediction system. It includes data processing pipelines for cricket match data, machine learning models for point prediction, and a full-stack web application for user interaction.
12% of Atlas Score
The repository contains three educational components: a machine learning assignment for text classification using embeddings and classical models, a Jupyter notebook demonstrating an LLM-based agent playing the 2048 game, and a script for sampling and plotting normal distributions.
10% of Atlas Score
This repository contains lab assignment solutions for a Natural Language Processing course, covering dataset collection, text processing, word embeddings, probabilistic modelling, and POS tagging.
7% of Atlas Score
tokenizer-hi is a course-assignment repository implementing a byte-level BPE tokenizer for Hindi from the Python standard library, with corpus building, training, encode/decode, dataset fetching via kagglehub, and pickle serialization of the trained vocab and merges.
