Heuristics Python Packages

gpuastar-experiments-cpp

GPU-Accelerated A* Search with Deep Neural Network Heuristics (SoCS 2026)

gpuastar-cpp

GPU-Accelerated A* Search with Deep Neural Network Heuristics (SoCS 2026)

opes

An open-source Python module for portfolio optimization and backtesting

qqa

Quasi-Quantum Annealing (QQA): a GPU solver for combinatorial & spin-glass optimisation — PyTorch library + live Streamlit dashboard. ICLR 2025.

evol

a python grammar for evolutionary algorithms and heuristics

anti-clustering

A Python library for anti-clustering algorithms

deriva-studio

Deriva uses knowledge graphs, heuristics, and LLMs to automatically derive architecture models from existing software repositories, reducing the manual burden on digital architects.

deriva-cli

Deriva uses knowledge graphs, heuristics, and LLMs to automatically derive architecture models from existing software repositories, reducing the manual burden on digital architects.

tspgrasp

A Greedy Randomized Adaptive Search Procedure (GRASP) for the Traveling Salesman Problem (TSP)

explodethosebits

CUDA-Accelerated exhaustive bit-tree/bit-explosion analysis for digital forensics.

gpuastar-cu

GPU-Accelerated A* Search with Deep Neural Network Heuristics (SoCS 2026)

neuroptimiser

NeurOptimiser is a neuromorphic optimisation framework in which metaheuristic search emerges from asynchronous spiking dynamics.

versatile-evasion-attacks

Security protocols for estimating adversarial robustness of machine learning models for both tabular and image datasets. This package implements a set of evasion attacks based on metaheuristic optimization algorithms, and complex cost functions to give reliable results for tabular problems.

ki

Hobbyist Library Combining Machine Learning with Heuristics, Tested Across Supervised and Reinforcement Domains

itemsubjector

CLI-tool to easily add "main subject" aka topics in bulk to groups of items on Wikidata

universal-evasion-attacks

Security protocols for estimating adversarial robustness of machine learning models for both tabular and image datasets. This package implements a set of evasion attacks based on metaheuristic optimization algorithms, and complex cost functions to give reliable results for tabular problems.

lk-heuristic

The Lin-Kernighan Heuristic implemented in python

rqmts

rqmts - Generate pip requirements.txt file for any project

gpuastar-experiments

GPU-Accelerated A* Search with Deep Neural Network Heuristics (SoCS 2026)

gpuastar

GPU-Accelerated A* Search with Deep Neural Network Heuristics (SoCS 2026)

articleparse

Heuristic text extraction from news sites in Python3