Skip to content
Atlas profile

Simon Strandgaard

@neoneyeVerified GitHub profile

Developer

AI-Atlas score

Advanced
0100
Strongest
AI Agents
62.4/100 domain score
Rank
24th=
of 86
Denmark
1st
of 1
  • DenmarkLocation
  • 14 Nov 2026Mapped
  • 17 / 232AI projects
01Skills matrix

AI Skills Matrix

AI Skills Matrix scores, 0 to 100
Machine Learning61
Computer Vision53
Data Science48
NLP & LLMs57
AI Agents62
MLOps32

Each node is one domain, scored only from evidence in these public repositories. Select one to see why.

Substantial implementations with real depth.

02Evaluated projects6 of 17

232 public repositories → 17 with AI work, evaluated. The other 215 (repositories without AI code, forks and empty repositories) are not scored and have no effect on the result. How repositories are selected

Ranked by contribution

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.

01
49.7

Implementation

18% of Atlas Score

Competition Solution· Python

image

This repository is a solution for the ARC Prize 2024 competition, implementing multiple approaches (LLM-based and decision tree-based) to solve abstract reasoning tasks using RLE-compressed puzzle representations. The committed state includes model code, dataset generation tools, and training notebooks, though the notebooks have not been executed to demonstrate training or evaluation results.

Machine Learning0.90Computer Vision0.80NLP & LLMs0.70Data Science0.60
arc-agiarc-prize-2024
02
54.5

Implementation

18% of Atlas Score

ML Application· Python

RainBox banner

RainBox is a personal assistant application that integrates local and remote language models, providing a web interface for model management, agent-based tasks, research capabilities, and benchmarking.

NLP & LLMs0.80Machine Learning0.70AI Agents0.60MLOps0.50
ai-agentharnesshome-assistantpersonal-assistant
03
47.5

Implementation

16% of Atlas Score

Educational Implementation· Jupyter Notebook

image

This repository contains code and experiments for attempting to solve the ARC Prize 2024 using large language models with RLE-based input compression. It includes data generation, model wrapping, inference scripts, and various proof-of-concept implementations, though the main training notebooks have not been executed.

Machine Learning0.90NLP & LLMs0.90Computer Vision0.80Data Science0.70
04
50.7

Implementation

15% of Atlas Score

Training Experiment

The repository implements a transformer-based model trained via reinforcement learning to solve ARC puzzles. It includes custom data generation through Q-learning-driven simulation, model training, and inference capabilities.

Machine Learning0.90NLP & LLMs0.80Data Science0.50AI Agents0.50
05
59.6

Advanced

+1.1 adoption

11% of Atlas Score

Educational Implementation· HTML

The agent-memory-atlas is a code-grounded field guide that documents and compares memory systems for AI agents, providing reports, patterns, and a comparative analysis to assist developers in understanding and selecting appropriate memory architectures.

AI Agents0.90Data Science0.30NLP & LLMs0.20
agent-memoryagent-memory-systemaiai-agentsai-memory
06
39.4

Implementation

7% of Atlas Score

Dataset / Data Pipeline· Python

This repository is a collection of datasets related to the Abstraction and Reasoning Corpus (ARC) and its variants, including 1D-ARC, ARC-Heavy, ARC-AGI-1, ARC-AGI-2, and others. It provides the datasets along with a few utility scripts for data format conversion and compression.

Data Science0.85NLP & LLMs0.50Computer Vision0.40
arc-agidatasetdatasets