ai-engineering-from-scratch
An open-source curriculum for learning AI engineering by implementing model internals, retrieval pipelines, and agent runtimes. Study through lessons, interactive labs, or staged coding projects, and inspect the code and evaluation results.
Pick a small issue you can reproduce, then fix it with your AI coding agent.
Share on XLicense: MIT
Overview
AI Engineering from Scratch is an open-source curriculum for learning how AI systems work by implementing their internals and testing the results. It covers model foundations, retrieval, LLM systems, and agent runtimes, with lessons and learning routes available on the website or for local study. Learners can use interactive labs and staged projects with starter code, reference implementations, and local graders, then keep code and evaluation results to inspect failures and compare systems.
Key features
- Lessons and learning routes on model foundations, LLM systems, and agents
- Interactive labs, including a gradient descent visualization
- Staged projects with starter code, reference implementations, and local graders
- Code and evaluation results to inspect failures and compare systems
Best for
Learners who want to understand AI engineering by building and testing components rather than only reading about them. It suits self-paced study on the website or with local code.
- Upstream
- rohitg00/ai-engineering-from-scratch
- Fork on GitHub
- Guo-astro/ai-engineering-from-scratch
- Upstream stars
- 76k
- Category
- AI agents and LLM tools
- Language
- Python
- License
- MIT
- Forked
- 2026-10-09
- Sync status
- Diverged from upstreamLast synced 2026-10-22
More in AI agents and LLM tools
/last30days is an AI-agent skill for researching recent discussions across social platforms, video, news, markets, and the web. It brings scattered signals together in a synthesized brief for trend research and preparation.
Forked 2026-10-22Last synced 2026-11-08License: MITAI agents and LLM toolsGitHub
A portable C99 inference engine for running Kimi K3 on a CPU without a GPU or machine-learning framework. It streams the large checkpoint from disk to support inference with limited RAM, for batch text generation or text chat.
Forked 2026-10-21Last synced 2026-11-08License: Apache-2.0AI agents and LLM toolsGitHub
LayerFS gives AI agents writable workspaces over shared history, so they can work in parallel without copying the base. Use it to checkpoint, branch, rewind, and merge agent changes.
Forked 2026-10-21Last synced 2026-11-08License: MITAI agents and LLM toolsGitHub
Magnitude runs open models locally and tunes kernels for your hardware. Use it to connect local models to supported agents or an OpenAI-compatible client.
Forked 2026-10-19Last synced 2026-11-08License: Apache-2.0AI agents and LLM toolsGitHub