Applying the Unix philosophy to neural networks

In plain words

This project applies Unix philosophy principles to neural network design and development. It's intended for machine learning engineers and developers who want to build modular, composable neural network systems. The approach emphasizes small, focused tools that work together effectively, rather than monolithic frameworks, offering an alternative perspective on how to structure deep learning projects.

written from the facts on this page · September 2026

• 
  Single neuron neural network written in COBOL2020 · github.com · ▲94

  A perceptron written in COBOL. Contribute to victorqribeiro/perceptronCobol development by creating an account on GitHub.

• 
  Deep Learning for Program Synthesis2017 · microsoft.com · ▲93

  By Rishabh Singh, Jacob Devlin, Abdelrahman Mohamed, and Pushmeet Kohli, Microsoft Research Despite the many advances in computing over the past decades, the actual process of writing computer software has not fundamentally changed — a programmer must manually code the exact algorithmic logic of a p

• 
  Neural networks tutorial series with code2020 · github.com · ▲107

  The simplest form of an artificial neural network explained and demonstrated. - GitHub - gokadin/ai-simplest-network: The simplest form of an artificial neural network explained and demonstrated.

• 
  LambdaNet – A functional neural network library written in Haskell2014 · github.com · ▲56

  Purely functional artificial neural network library implemented in Haskell. - jbarrow/LambdaNet

• N5
  NN-512 – Generate standalone C code for neural nets2020 · nn-512.com · ▲111
• 
  NeuroBlockFeb 2026 · neuro-block.com · ▲120

  No-code AI Lab: Train models, access datasets, run inference

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 19d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 18d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 20d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 22d ago · stillwet.art

• 
  Beam.win▲378

  Run AI agents on one Mac and use its windows on another

  AI · 5d ago · beam.win

• 
  FastRouter.ai▲364

  Route requests to the right LLM for cost, latency & quality

  AI · 23d ago · fastrouter.ai

• 
  Jumbo: Privacy & Security▲936

  Your privacy assistant, by Sunrise co-founder

  Life & fun · 2019 · apps.apple.com

• 
  Lorem Picsum – Lorem Ipsum but for photos▲880

  Lorem Ipsum... but for photos

  Life & fun · 2019 · picsum.photos

• 
  UserGuiding 2.0▲782

  An easy way to show how your product works 😻

  Work · 2019 · userguiding.com

• 
  Startup 3▲745

  Create websites and landing pages with Startup 3 🚀

  Dev tools · 2019 · designmodo.com

• 
  1MB – Free and easy static website hosting and database▲744

  Unlock the full potential of your website with 1MB

  Dev tools · 2019 · 1mb.site

• 
  Mercury▲730

  Banking stack for startups

  Commerce · 2019 · mercury.com