freshcrate
Skin:/
Language:English/็ฎ€ไฝ“ไธญๆ–‡
Home > MCP Servers > ai-engineering-from-scratch

ai-engineering-from-scratch

Learn it. Build it. Ship it for others.

agentsaiai-agentsai-engineeringcomputer-visioncoursedeep-learningfrom-scratchmcppython
Why this rank:Strong adoptionRecent releaseHealthy release cadence

Description

Learn it. Build it. Ship it for others.

README

๐Ÿ’ฌ "84% of students already use AI tools. Only 18% feel prepared to use them professionally.

This course closes that gap."

272+ lessons. 20 phases. ~306 hours. From linear algebra to autonomous agent swarms. Python, TypeScript, Rust, Julia. Every lesson produces something reusable: prompts, skills, agents, and MCP servers.

You don't just learn AI. You learn AI with AI. Then you build real things. Then you ship tools others can use.


๐Ÿ†š Why This Course?

๐Ÿ“บ Traditional Courses ๐Ÿง  This Course
Scope
One slice (NLP or Vision or Agents)		 Scope
๐ŸŒ Everything โ€” math ยท ML ยท DL ยท NLP ยท vision ยท speech ยท transformers ยท LLMs ยท agents ยท swarms
Languages
Python only		 Languages
๐Ÿ Python ยท ๐ŸŸฆ TypeScript ยท ๐Ÿฆ€ Rust ยท ๐ŸŸฃ Julia
Output
"I learned something"		 Output
๐Ÿ“ฆ A portfolio of tools, prompts, skills, and agents you can install
Depth
Surface-level or theory-heavy		 Depth
๐Ÿ”ฌ Build from scratch first, then use frameworks
Format
Videos you watch		 Format
๐Ÿ’ป Runnable code + docs + web app + AI-powered quizzes
Style
Passive consumption		 Style
๐Ÿค– AI-native โ€” Claude Code skills test you as you go

๐Ÿค– AI-Native Learning

This isn't a course you watch. It's a course you use with your AI coding agent.

๐ŸŽฏ Learn with AI, not just about AI

# ๐Ÿงช Find where to start based on what you already know
/find-your-level

# โœ… Quiz yourself after completing a phase
/check-understanding 3

# ๐Ÿ“ฆ Every lesson produces a reusable artifact
ls phases/03-deep-learning-core/05-loss-functions/outputs/
# โ”œโ”€โ”€ prompt-loss-function-selector.md
# โ””โ”€โ”€ prompt-loss-debugger.md

๐Ÿ› ๏ธ Built-in Claude Code Skills

๐ŸŽด Skill โšก What it does
find-your-levelcheck-understanding

๐Ÿšข Every Lesson Ships Something

Other courses end with "congratulations, you learned X." Our lessons end with a reusable tool:

๐Ÿ“
Prompts
Paste into any AI assistant for expert-level help

๐ŸŽด
Skills
Install into Claude Code, Cursor, or any agent

๐Ÿค–
Agents
Deploy as autonomous workers

๐Ÿ”Œ
MCP Servers
Plug into any MCP-compatible AI app

277-term searchable glossary. Full lesson catalog. ~306 hours of content with per-lesson time estimates.
๐ŸŒ Browse the website โ†’

๐Ÿ—บ๏ธ The Journey

20 phases ยท 272+ lessons ยท click any phase to expand

Phase 0Phase 1Phase 2Phase 3Phase 4Phase 5Phase 6Phase 7Phase 8Phase 9Phase 10Phase 11Phase 12Phase 13Phase 14Phase 15Phase 16Phase 17Phase 18Phase 19Legend: BuildLearn

๐Ÿ› ๏ธ Get your environment ready for everything that follows.

# Lesson Type Lang
01 Dev Environment Build02 Git & Collaboration Learn03 GPU Setup & Cloud Build04 APIs & Keys Build05 Jupyter Notebooks Build06 Python Environments Build07 Docker for AI Build08 Editor Setup Build09 Data Management Build10 Terminal & Shell Learn11 Linux for AI Learn12 Debugging & Profiling Build ๐ŸŸฃ Phase 1 โ€” Math Foundations ย 22 lessonsย  The intuition behind every AI algorithm, through code.
# Lesson Type Lang
01 Linear Algebra Intuition Learn02 Vectors, Matrices & Operations Build03 Matrix Transformations & Eigenvalues Build04 Calculus for ML: Derivatives & Gradients Learn05 Chain Rule & Automatic Differentiation Build06 Probability & Distributions Learn07 Bayes' Theorem & Statistical Thinking Build08 Optimization: Gradient Descent Family Build09 Information Theory: Entropy, KL Divergence Learn10 Dimensionality Reduction: PCA, t-SNE, UMAP Build11 Singular Value Decomposition Build12 Tensor Operations Build13 Numerical Stability Build14 Norms & Distances Build15 Statistics for ML Build16 Sampling Methods Build17 Linear Systems Build18 Convex Optimization Build19 Complex Numbers for AI Learn20 The Fourier Transform Build21 Graph Theory for ML Build22 Stochastic Processes Learn ๐Ÿ”ต Phase 2 โ€” ML Fundamentals ย 18 lessonsย  Classical ML โ€” still the backbone of most production AI.
# Lesson Type Lang
01 What Is Machine Learning Learn02 Linear Regression from Scratch Build03 Logistic Regression & Classification Build04 Decision Trees & Random Forests Build05 Support Vector Machines Build06 KNN & Distance Metrics Build07 Unsupervised Learning: K-Means, DBSCAN Build08 Feature Engineering & Selection Build09 Model Evaluation: Metrics, Cross-Validation Build10 Bias, Variance & the Learning Curve Learn11 Ensemble Methods: Boosting, Bagging, Stacking Build12 Hyperparameter Tuning Build13 ML Pipelines & Experiment Tracking Build14 Naive Bayes Build15 Time Series Fundamentals Build16 Anomaly Detection Build17 Handling Imbalanced Data Build18 Feature Selection Build ๐ŸŸข Phase 3 โ€” Deep Learning Core ย 13 lessonsย  Neural networks from first principles. No frameworks until you build one.
# Lesson Type Lang
01 The Perceptron: Where It All Started Build02 Multi-Layer Networks & Forward Pass Build03 Backpropagation from Scratch Build04 Activation Functions: ReLU, Sigmoid, GELU & Why Build05 Loss Functions: MSE, Cross-Entropy, Contrastive Build06 Optimizers: SGD, Momentum, Adam, AdamW Build07 Regularization: Dropout, Weight Decay, BatchNorm Build08 Weight Initialization & Training Stability Build09 Learning Rate Schedules & Warmup Build10 Build Your Own Mini Framework Build11 Introduction to PyTorch Build12 Introduction to JAX Build13 Debugging Neural Networks Build ๐ŸŸ  Phase 4 โ€” Computer Vision ย 28 lessonsย  From pixels to understanding โ€” image, video, 3D, VLMs, and world models.
# Lesson Type Lang
01 Image Fundamentals: Pixels, Channels, Color Spaces Learn02 Convolutions from Scratch Build03 CNNs: LeNet to ResNet Build04 Image Classification Build05 Transfer Learning & Fine-Tuning Build06 Object Detection โ€” YOLO from Scratch Build07 Semantic Segmentation โ€” U-Net Build08 Instance Segmentation โ€” Mask R-CNN Build09 Image Generation โ€” GANs Build10 Image Generation โ€” Diffusion Models Build11 Stable Diffusion โ€” Architecture & Fine-Tuning Release History
VersionChangesUrgencyDate
v2026.10.4Highlight what matters, keep notes beside the text, and carry a compact reference into your next build. This edition adds a reading workspace, 154 cheat sheets, and the ready edition of SGLang 101. [Start learning](https://aiengineeringfromscratch.com) ยท [Cheat sheets](https://aiengineeringfromscratch.com/cheatsheets) ยท [SGLang 101](https://aiengineeringfromscratch.com/manual-sglang-101.html) ## Highlights and notes Select text in a lesson or manual, choose one of four colors, and add a note.High10/19/2026
v2026.10.3Edition 2026.10.3 adds a reverse engineering track, a third manual, and LaTeX math in the lessons. The curriculum grows from 523 to **542 lessons across 20 phases**. ## Learn reverse engineering Fourteen new Phase 13 lessons teach how to read a compiled program you built yourself, from file bytes to evidence-backed pseudocode (#597). - The lessons cover program anatomy (ELF, Mach-O, PE), disassembly and control-flow graphs, lifting to IR and SSA, calling conventions on System V, Windows x64 aHigh10/15/2026
v2026.10.2Edition 2026.10.2 adds a second manual, a public API and MCP server for the curriculum, and fixes across the site. The curriculum stays at **523 lessons across 20 phases**, with 2 lesson texts revised since Edition 2026.10.1. ## Read Docker Sandboxes and Docker Agent 101 [Docker Sandboxes and Docker Agent 101](https://aiengineeringfromscratch.com/manual-docker-sandboxes-101) explains Docker Sandboxes (`sbx` 0.47.0) and Docker Agent (`docker-agent` 1.149.0), from their purpose to each command, High10/10/2026
v2026.10.1Edition 2026.10.1 adds the first long-form manual, a catalog of 100 projects, and fixes across the site. The curriculum stays at **523 lessons across 20 phases**, with 3 lesson texts revised since Edition 2026.10. ## Read A2A 101, the first manual [A2A 101](https://aiengineeringfromscratch.com/manual-a2a-101.html) explains the Agent2Agent protocol at v1.0.1, from its purpose to each request and response. It has 28 sections in 7 parts, 7 reference sections, and 31 figures. The PDF is attached bHigh10/6/2026
v2026.10Edition 2026.10 adds exam prep for the Model Context Protocol Associate (MCPA) certification, translates the site interface around every lesson, and holds the course to stricter checks. The curriculum stays at **523 lessons across 20 phases**, with 58 lesson texts revised since Edition 2026.09. CI now runs the lessons' own tests, and a sweep repaired datasets, models, tools, and links that no longer resolve. ## Prepare for the MCPA exam The new [MCPA certification prep](https://aiengineeringfrHigh9/27/2026
v2026.09The September edition brings the curriculum to **523 lessons across 20 phases**, with 20 new lessons and 21 revised lesson texts since Edition 2026.08. It adds learning paths for real engineering work, expands Agent Skills and MCP practice, and improves the experience of moving between the website, repository, and terminal. ## Choose a path through the curriculum The new [AI Engineering Learning Paths](https://aiengineeringfromscratch.com/learning-paths.html) organize the course into four coreHigh9/7/2026
v2026.08The August edition. Three big surfaces landed: a certification prep program, the course in five languages, and a rebuilt way to navigate all 503 lessons. ## Certification prep, free and build-first A new [certifications section](https://aiengineeringfromscratch.com/certifications.html) turns public exam blueprints into study paths you build through, not read through. The first program covers all four Claude credentials from the July 2026 exam guides (Associate, Developer, Architect FoundationsHigh8/10/2026
v2026.07First book edition. EPUB and PDF for all six volumes are built by CI from the lesson sources and attached to this release automatically; allow the build a few minutes to upload them. The download links on the site and README always point at the newest release.High7/25/2026
main@2026-06-25Latest activity on main branchHigh6/25/2026
0.0.0No release found โ€” using repo HEADHigh4/21/2026

Dependencies & License Audit

Loading dependencies...

Similar Packages

DeepMCPAgentModel-agnostic plug-n-play LangChain/LangGraph agents powered entirely by MCP tools over HTTP/SSE.v1.10.1
agentic-codingAgentic Coding Rules, Templates etc...main@2026-10-24
KilnDescribe it or draw it. Kiln makes it real. โ€” 461 MCP tools for AI-agent-controlled 3D printing. OctoPrint, Moonraker, Bambu Lab, Prusa Link, and Elegoo.v1.5.0
mcp-scannerScan MCP servers for potential threats & security findings.4.8.7
kagglerun๐Ÿš€ Run Python on Kaggle's free GPUs directly from your terminal without the need for a browser, streamlining your data science workflow.master@2026-10-14

More from rohitg00

agentmemoryPersistent memory for AI coding agents
kubectl-mcp-serverPublished in CNCF Landscape: A MCP server for Kubernetes.

More in MCP Servers

litellmPython SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropi
ruflo๐ŸŒŠ The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade archit
@claude-flow/cliRuflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code
claude-plugins-officialOfficial, Anthropic-managed directory of high quality Claude Code Plugins.