#computational-graph Repositories
Discover 9 active open source GitHub repositories tagged with #computational-graph, accumulating 43,796 total stars (averaging 4,866 stars per project). Leading this topic is karpathy/micrograd with 19,036 stars.
9 repositories total
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
Code samples for my book "Neural Networks and Deep Learning"
Inspect, visualize, and intervene in any operation in any neural network. Capture every activation and gradient, the full computational graph, and 800+ metadata fields without changing model code. Supports PyTorch, JAX, TensorFlow, MLX, PaddlePaddle, and tinygrad. Validated on 6,400+ models. Built for researchers and their AI agents.
Frequently Asked Questions
What is the most popular #computational-graph repository on GitHub?
The top ranked open source #computational-graph project on GitHub is karpathy/micrograd with 19,036 stars. A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
Which programming languages are most used in #computational-graph repositories?
Among the top ranked #computational-graph projects on GitHub, the most common programming languages are Python, Jupyter Notebook, TypeScript, C.
How is the #computational-graph repository ranking calculated?
We track 9 active open source repositories tagged with #computational-graph (500+ stars), totaling 43,796 stars with an average of 4,866 stars per repository. Rankings update daily from the GitHub API.