Andrey Markin
  • home
  • blog
  • projects
  • services
  • directory
    • Tool
    • Library
    • Repo
    • Article
    • XTweet
    • Guideline
  • about
  • contact
  • meet

Mark Life Ltd

  1. Home
  2. Directory
  3. Tfjs Zero To Hero
Meet

Mark Life Ltd

BG208147965

HomeContactPrivacyLLM-friendlyBlog RSSDirectory RSS
  1. Directory
  2. tfjs-zero-to-hero
RepoMachine LearningOpen Sourcetypescriptmllearning

tfjs-zero-to-hero

Re-implementing classic ML models in TypeScript with @tensorflow/tfjs-node, following Andrej Karpathy's Neural Networks. Zero to Hero. Final destination — a from-scratch two-tower retrieval model on MovieLens.

Added May 16, 2026
Visit repo

Most ML projects, courses, and tutorials are Python — that's the default. I'm taking a different route: following Andrej Karpathy's Neural Networks: Zero to Hero (which is PyTorch) but re-implementing each model in TypeScript against the equivalent TensorFlow.js APIs.

The thing is — the actual ML doesn't happen in Python. It happens in C and CUDA. Python is mostly a thin API layer over native kernels. TF.js is the same story: @tensorflow/tfjs-node binds into the C++ TensorFlow runtime. So the "Python advantage" for ML is more cultural than technical.

Given I write TypeScript day-to-day and most modern application code is TypeScript, doing ML in TS means the model ships in the same stack as the product that consumes it — no Python sidecar, no FastAPI bridge, no language boundary at inference time. Feels like a unique and underexplored angle.

Progression: TF.js fundamentals → MNIST → makemore (bigram → MLP → BatchNorm → WaveNet) → micrograd → nanoGPT → two-tower retrieval on MovieLens with a Next.js + shadcn demo UI.

Related

  • ExecutorOpen-source tool gateway for agents from Rhys Sullivan. Normalizes MCP, OpenAPI, GraphQL, and custom sources into one typed SDK that agents call in a sandbox — built on Cloudflare's Code Mode pattern.
  • HexOpen-source, fully native macOS voice-to-text app using local Parakeet TDT v3 models with zero network calls. Press-and-hold a hotkey to record, release to paste the transcript anywhere.
  • SciraOpen-source agentic research platform that plans, retrieves, and returns cited answers across 17 search modes.
  • telegram-claudeTelegram bot interface for Claude Code on a VPS. Message the bot, it spawns Claude Code in the selected project directory and streams results back — voice notes, streaming responses, session continuity, plan-mode interception.