Highlights
Lists (8)
Sort Name ascending (A-Z)
Competitions ⚔️
This is where I store my most recent competitions and hackathons📖Education Resources
HPC
HPC projectsInfra/ Low level
Infra projects and low level projectsOld Nexa_Projects
A bunch of repo's I never finished and are archivedResearch/Cool Ideas I found
A bunch of Repo's and experimental stuff that I find coolSciML
All work in SciMLTools
A bunch of tools I personally useStarred repositories
Skills for Real Engineers. Straight from my .claude directory.
Protein-Ligand Interaction Profiler - Analyze and visualize non-covalent protein-ligand interactions in PDB files according to 📝 Schake, Bolz, et al. (2025), https://doi.org/10.1093/nar/gkaf361
A feed-forward 3D foundation model for reconstructing scenes from streaming data
CORAL is a robust, lightweight infrastructure for multi-agent autonomous self-evolution, built for autoresearch.
An automated scoring function to facilitate and standardize the evaluation of goal-directed generative models for de novo molecular design
A series of high-performance GEMM (General Matrix Multiply) implementations Iteratively optimised for H100 GPUs in Pure CUDA.
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
NVIDIA Linux open GPU kernel module source
The easiest, most secure way to use WireGuard and 2FA.
The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.
Fused Conv2d+Tanh+Scale+Bias+MaxPool2d CUDA kernel. 22.5x faster than PyTorch on RTX 3090.
Hierarchical Generation of Molecular Graphs using Structural Motifs
MolTrans: Molecular Interaction Transformer for Drug Target Interaction Prediction (Bioinformatics)
Quasar Attention Continuous-Time Memory Dynamics for Scaling Models Context to Millions of Tokens
FastMCP 3.2 server and webapp wrapping the World Labs Marble API — generate navigable 3D worlds from text, images, and video
GraphDTA: Predicting drug-target binding affinity with graph neural networks
Control panel for VLLM, Sglang, llama.cpp, exllamav3
An aesthetically pleasing YouTube TUI written in Rust
Train the smallest LM you can that fits in 16MB. Best model wins!
Muon is an optimizer for hidden layers in neural networks
ReadyAI (readyai.ai) enables structured data processing at scale, democratizing access to the valuable digital commodity of structured data – the key ingredient for high quality fine tuned models a…
⚡ Dynamically generated stats for your github readmes