gugugu12138/AdaptoFlux
An algorithm that implements intelligence based on a Method pool (a collection containing multiple types of functions). 一种基于方法池（包含多种类型的函数的集合）实现智能的算法
AdaptoFlux is a new machine learning framework that helps you build intelligent systems by combining pre-existing knowledge blocks, called "methods," in a dynamic way. Instead of training models from scratch, you feed in your data, and it generates an optimized data processing pipeline (a data flow graph) that can learn and adapt. This tool is ideal for scientists, researchers, or AI developers working on symbolic regression, few-shot learning, or game AI.
Use this if you need to build flexible, interpretable AI models that can reuse knowledge across different tasks, especially in areas like symbolic regression, small-sample learning, or game AI.
Not ideal if you primarily work with large-scale deep learning models that rely heavily on gradient-based optimization for numerical computation, or if you require extensive vectorization support.
Stars
50
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gugugu12138/AdaptoFlux"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
nschaetti/EchoTorch
A Python toolkit for Reservoir Computing and Echo State Network experimentation based on...
metaopt/torchopt
TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
gpauloski/kfac-pytorch
Distributed K-FAC preconditioner for PyTorch
opthub-org/pytorch-bsf
PyTorch implementation of Bezier simplex fitting
pytorch/xla
Enabling PyTorch on XLA Devices (e.g. Google TPU)