Repository Index

reinfore learning tool box, contains trpo, a3c algorithm for continous action space

Multi-stage Riemannian flow matching for physically valid molecular docking, with GNINA scoring, PoseBusters filtering, CLI inference, and benchmarks.

• alphafold3
• docking
• drug-design
• drug-discovery

Spatial Transformer Nets in TensorFlow/ TensorLayer

• tensorlayer
• tensorflow
• cnn
• deep-learning

A little logger for machine learning research

Python3 script that transfers files in Google Colab 10-50x faster, using multi-threaded parallel copying between Google Drive locations.

• colab-notebook
• multithreading
• parallel-computing
• copy

HistoClean is a tool for the preprocessing and augmentation of images used in deep learning models. This easy to use application brings together the most popular image processing packages from across the python universe, meaning no more looking at documentation! HistoClean provides real time feedback to augmentations and preprocessing options. This allows users to evaluate their steps before implementation.

• image-processing
• images
• image-analysis
• deep-learning

3D shape analysis using deep learning

• cancer-biology
• cell-biology
• deep-learning
• geometric-deep-learning

An interactive tool for segmenting yeast cells using deep learning.

Generate a summarized description of a body of text

• machine-learning
• docker-image
• deep-neural-networks
• tensorflow-models

A structured, multi-agent Claude Code learning environment for mastering Retrieval-Augmented Generation (RAG)

Accurate segmentation of bacterial microscope images using deep learning synthetically generated image data.

• microscopy
• image-processing
• segmentation
• biology

Tool for suggesting lemma names in Coq verification projects

• coq
• machine-learning
• name-generation
• pytorch

German small and large versions of GPT2.

• gpt2
• german
• common-crawl
• machine-learning

Machine learning on dirty tabular data (legacy clone of skrub)

Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.

• agentic-ai
• ai-safety
• fastapi
• langchain

Generative models for transcriptomic-driven or protein-driven molecular design (PaccMann^RL).

• deep-reinforcement-learning
• generative-model
• vae
• molecule-generation

TensorLight - A high-level framework for TensorFlow

• tensorflow
• framework
• deep-learning
• machine-learning

A Python framework that uses machine learning algorithms to implement the metadata recovery attack against obfuscated programs.

Open BTC 5-minute prediction market sandbox for AI agents — register with one API call, get 1,000 test credits, and place a live order

• ai-agents
• prediction-markets
• starter-template
• trading-bot

Conflict-free merge for DataFrames, JSON, ML models & distributed agents — powered by CRDTs. The first merge library where every operation is mathematically guaranteed to converge.

• collaborative-editing
• conflict-resolution
• crdt
• data-engineering

Ceci n'est pas une pomme - Deep Learning on mobile device

Golem Image Classifier is built using the Service API of Yapapi to interact with the Golem Network (golem.network). Built as part of a Gitcoin Bounty

• machine-learning
• golem
• yagna

A lightweight Python package for teaching computational methods through art history. Extract and analyze artist-specific works from WikiArt with built-in visualizations. Designed for digital humanities and computational design courses. Features genre/style analysis, matplotlib integration, and pedagogical clarity over algorithmic complexity.

• art-history
• color-analysis
• color-extraction
• color-palette

gtfs2vec - Learning GTFS Embeddings for comparing PublicTransport Offer in Microregions