Education●Mid
A complete, containerized data engineering learning platform
Curated collection of existing tools with a structured curriculum—useful but not novel.
Niche GemShip It
MarlonPro
113mo ago
Back to browse
AI Engineering AI-native Self-learning course repo
by rohitghumare·Mar 31, 2026·1 point·0 comments
AI Analysis
●●SolidRabbit HoleBig BrainCrowd Pleaser
Implement transformers and LLMs from raw math in Python, Rust, TypeScript, and Julia.
Strengths
- •Multi-language implementation forces deeper understanding than standard Python-only tutorials.
- •Covers full stack from calculus foundations to production deployment scenarios.
- •Open source MIT license allows free forkable curriculum without paywalls.
Weaknesses
- •Many phases still marked "Planned" or "In-Progress" on the roadmap.
- •Maintaining four language versions simultaneously creates a massive maintenance burden.
Category
Target Audience
Aspiring AI engineers, developers
Similar To
Andrej Karpathy's Zero to Hero · Fast.ai · Hugging Face Course
Similar Projects
Education●Mid
I built a self-hosted course platform in Clojure
Clojure learning hub, but Coursera/Udemy already own education at scale.
Niche GemCozy
jacekschae
59133mo ago
Education●●Solid
Tiny-vLLM – high performance LLM inference engine in C++ and CUDA
Build vLLM from scratch with PagedAttention kernels when llama.cpp already exists.
Big BrainNiche Gem
yu3zhou4
2051820d ago
Developer Tools●●Solid
We help engineers understand codebases with interactive missions
Debugging missions beat Q&A — structured challenges instead of chatting with codebases.
Big BrainSolve My Problem
AfthabShiraz
413mo ago
Education●●Solid
The Department of Words
Math through language metaphor is clever, but courses are static reference pages, not interactive learning.
Big BrainEye CandySolve My Problem
Falimonda
113mo ago
Infrastructure●●Solid
Spawn – Deploy and Self-Heal Any GitHub Repo
It uses an LLM not just for scaffolding but as an active repair agent: Claude generates Dockerfiles, diagnoses crashes (diagnoseCrash) and can trigger redeploys or memory scaling. The architecture ties BullMQ, Fly Machines and a 30s health loop into a real feedback loop — clever and ambitious, but it also leans heavily on Claude + Fly/Supabase so expect nontrivial setup and vendor/LLM dependency.
WizardryBold Bet
gauravguitara
104mo ago