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.
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
- 66k
- Category
- AI agents and LLM tools
- Language
- Python
- License
- MIT
- Forked
- 2026-10-09
- Sync status
- In syncLast synced 2026-10-10
More in AI agents and LLM tools
A small, hackable character-level language model that learns patterns from line-based text files and generates similar items, such as name ideas.
Forked 2026-10-09Last synced 2026-10-10License: MITAI agents and LLM toolsGitHub
uzu is an inference engine for running AI models in apps, helping developers keep inference on-device instead of relying on remote services. Use it to download a model and build chat features.
Forked 2026-10-09Last synced 2026-10-10License: MITAI agents and LLM toolsGitHub
Anti Slop gives AI coding agents rules to avoid generic UI, filler text, and AI-shaped code. Use it as a filter alongside your own design direction.
Forked 2026-10-08Last synced 2026-10-10License: MITAI agents and LLM toolsGitHub
Apache Maka is an agent workspace that records every run, tool action, and model decision so work can be reviewed, recovered, and repeated with a clear trace.
Forked 2026-10-08Last synced 2026-10-10License: Apache-2.0AI agents and LLM toolsGitHub