ai-engineering-from-scratch

ai-engineering-from-scratch is an agent framework - Learn AI Engineering! Learn it. Build it. Ship it for others.

Overview

Implement model internals, retrieval pipelines, and agent runtimes. Test them, inspect failures, and keep the code and evaluation results.

Free, open source, MIT. Learn on the website, with a coding agent, or by running local code.

Your support keeps every lesson free and open source. See all supporters · Become a sponsor

Twenty starting points follow gradient descent on a quadratic loss. The graph shows their positions and mean loss after each update.

Three projects with staged starters, reference implementations, and local graders. Run commands from the repository root after setup. Starters fail until you implement the stages.

A candidate improves mean NDCG while one query ranks its most relevant evidence lower. Build a query-by-query comparison that reports the regression and can fail a release check.

Use Python 3.10+. Review RAG and model evaluation. Implement ranking validation, precision and recall, rank-sensitive metrics, then system comparison.

Keep: a reproducible comparison with per-query deltas and the judgments used to score them. Metrics describe those judgments; they do not establish answer correctness.

A supplied trace still takes 100 ms, but total token usage rises by 200 and one span starts failing. Separate overlapping child work from parent execution time, then produce a report that exposes the change.

ai-engineering-from-scratch is open-source, written primarily in Python, with 69,173 GitHub stars under the MIT license. The latest release is v2026.10.2 (2026-10-10).

Key capabilities

From the project's documentation:

• You can write code (any language; Python helps).
• You want to understand how AI actually works, not just call APIs.
• Attention Is All You Need — Vaswani et al., 2017 → Phase 7
• Language Models are Few-Shot Learners (GPT-3) → Phase 10
• Denoising Diffusion Probabilistic Models → Phase 8
• InstructGPT / RLHF → Phase 10

How it fits a local-AI stack

ai-engineering-from-scratch runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related agent frameworks in the directory:

• "Agent-Reach"
• "agentic-inbox"
• Agno
• "ai-agents-from-scratch"

Sources

• Source code & docs: rohitg00/ai-engineering-from-scratch
• Official website: https://aiengineeringfromscratch.com

Stats from GitHub, 2026-10-15.