Keras-style Python framework for building, training and deploying LM-based apps such as RAG systems, tool-using agents and MCP servers.
46447PythonApache-2.0Well maintainedUpdated 12 hours ago
#keras
Best open-source Keras deep learning tools and models (2026)
Keras tools range from pretrained model libraries to converters that target hardware. When picking one, check which backend it runs on and whether you need pretrained weights or a training framework. keras-hub offers pretrained text, image and audio models for Keras 3 that run on JAX, TensorFlow or PyTorch. hls4ml converts Keras, PyTorch and ONNX networks into HLS code for FPGA inference, and neural-structured-learning adds graph and adversarial signals to TensorFlow training.
Sort:Recently added
6 repositories
A Chinese-language 100-day machine learning course with Python code, notes and exercises, covering Day 1 to 54 so far.
22.2K5.5KPythonMITWell maintainedUpdated 15 days ago
A bilingual-docs collection of Python and Jupyter examples for AI-driven stock trading, covering learning materials, backtests, alpha mining, LLM stock forecasting and live-trading simulation.
6.7K+8 this week1.2KJupyter NotebookApache-2.0Updated 11 days ago
A Python package that converts Keras, PyTorch and ONNX neural networks into HLS code for running ML inference on FPGAs.
2.2K+4 this week615PythonApache-2.0Updated 3 days ago
A pretrained model library for Keras 3 offering text, image, and audio models that run on JAX, TensorFlow, or PyTorch.
997+1 this week377PythonApache-2.0Well maintainedUpdated yesterday
A TensorFlow framework for training neural networks with graph-structured or adversarially perturbed signals alongside input features.
1K191PythonApache-2.0Updated last month