Rare find

AioWay. A tool that builds and optimizes deep learning models from plain descriptions instead of code.

aioway.rentruewang.com

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

July 2026
  • 🌗 Contrastive loss (#417)
  • 〽️ NMF implementation (#405)
  • 🖌️ Update style guide (#413)
  • 🤵‍♂️ CODEOWNERS (#408)
  • 🛸 Improve `Space` casting (#402)
  • 🐫 Sphinx API docs (#403)
  • 🧹 Tidy up `aioway.torch.nn` (#400)
  • ✂️ Split spaces and casting modules (#396)
  • 👨🏻‍💼 Profiler for `UFunc` (#395)
  • 🛫 V0.0.13 release branch (#394)
  • 🧑‍💻 Hacky `fit` / `predict` api (#393)
  • 💱 Space coercion (#391)
  • 👉 Is-A coercion between `Space`s (#389)
  • 🌱 Contributing guidelines. (#365)
  • 🧪 `Space` and `Attr` improvements (#387)
  • 👟 Simple `Trainer` tasks interface (#385)
  • 🌱 Connect IO with `Env`s automatically (#384)
  • 🏋️ Support `gymnasium`-like `Space`s (#383)
  • 🔬 Support `sklearn` algorithms (#381)
  • 🎉 V0.0.12 release. (#380)
  • 🔋 Code generation for compounds. (#379)
June 2026
  • 📢 API module. (#378)
  • 💡 Add MLP `Emitter`. (#375)
  • 🎼 Composed `UFunc`. (#370)
  • 🏭 Generic `Thunk` types for `UFunc`. (#373)
  • 💥 Refactor core into thunks, ufuncs, iters (#369)
  • 🧱 Structure iterator (#367)
  • 🚀 v0.0.11 release (#364)
  • 🏁 Emitter and baselines, envs implementation (#363)
  • 🏟️ Get stages based on indicators (#362)