microsoft/archai
Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.
This tool helps machine learning engineers and researchers automatically design and optimize deep learning models for specific tasks like text generation or face segmentation. You provide a general search space for neural networks and define your optimization goals (e.g., speed, memory usage), and it outputs efficient, high-performing model architectures tailored to your needs. This is for AI practitioners who build and deploy deep learning solutions.
482 stars. Available on PyPI.
Use this if you need to efficiently find optimal deep neural network architectures for specific performance requirements without extensive manual experimentation.
Not ideal if you are looking for a pre-trained model or a simple framework for training existing architectures, rather than designing new ones.
Stars
482
Forks
93
Language
Python
License
MIT
Category
Last pushed
Nov 24, 2025
Commits (30d)
0
Dependencies
14
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/microsoft/archai"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pykt-team/pykt-toolkit
pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models
google-research/morph-net
Fast & Simple Resource-Constrained Learning of Deep Network Structure
IDEALLab/EngiBench
Benchmarks for automated engineering design
AI-team-UoA/pyJedAI
An open-source library that leverages Python’s data science ecosystem to build powerful...
automl/neps
Neural Pipeline Search (NePS): Helps deep learning experts find the best neural pipeline.