flwrlabs/flower
Flower: A Friendly Federated AI Framework
Supports pluggable aggregation strategies (FedAvg, FedProx, FedNova, and custom variants) and works framework-agnostic across PyTorch, TensorFlow, JAX, scikit-learn, XGBoost, and mobile platforms (TFLite, CoreML). Clients and servers communicate via gRPC with automatic reconnection, enabling horizontal scaling from edge devices to cloud infrastructure. Includes research-ready baselines reproducing published FL algorithms and supports both synchronous federated learning and custom message protocols for specialized applications.
6,705 stars. Actively maintained with 164 commits in the last 30 days.
Stars
6,705
Forks
1,158
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
164
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/flwrlabs/flower"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
OpenMined/PySyft
Perform data science on data that remains in someone else's server
zama-ai/concrete-ml
Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on...
p2pfl/p2pfl
P2PFL is a decentralized federated learning library that enables federated learning on...
JonasGeiping/breaching
Breaching privacy in federated learning scenarios for vision and text
secretflow/secretflow
A unified framework for privacy-preserving data analysis and machine learning