Turns regular JavaScript code into a differentiable neural net: if-else, loops and state are compiled into matrix multiplications and ReLU with no training. Runs on JS or WebGPU.
Useful for
- Compile existing JS code into a differentiable form to train its weights
- Speed up search over 100k JSON documents using GPU parallelism
- Attach a frozen program to a neural net and train them end-to-end
Before using
- License: MIT
- Installation and requirements have not been verified; review the README before running
Why now
- Created on GitHub
- 2026-10-15 UTC
- First seen by GitNova
- 2026-10-15 UTC
- Magnitude
- 8.0 / 10 · growing interest
Not enough consecutive complete history days to compare daily gains
Measured: October 15, 2026, 18:39 UTC
Measurement details
- Created on GitHub: 2026-10-15; first seen by GitNova: 2026-10-15 (UTC)
- +669 stars measured 2026-10-15, 06:44–18:19 UTC
- Not enough consecutive complete history days to compare daily gains
- Magnitude 8.0/10