Source-to-Source Debuggable Derivatives in Pure Python
Appears on
Quick read
Latest capture 2026-10-06 03:10
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
0 paths
Agent instructions and tool configuration found in this repository.
No config files detected.
9 observed captures since 2026-05-22. Observed captures are shown by default.
Stars from first capture +4
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Efficiently computes derivatives of NumPy code.
A deep learning framework built on an autograd engine with high level abstractions and low level control.
:chart_with_upwards_trend: Adaptive: parallel active learning of mathematical functions
A deep learning framework built on an autograd engine with high level abstractions and low level control.
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
High-performance TensorFlow library for quantitative finance.
