GStars
    rohitg00

    rohitg00/ai-engineering-from-scratch

    #50 this week

    Learn AI Engineering! Learn it. Build it. Ship it for others.

    ai
    ai-agents
    computer-vision
    education
    deep-learning
    llm
    machine-learning
    nlp
    agents
    ai-engineering
    course
    dsh
    from-scratch
    Python
    MIT
    77.8K stars
    13.8K forks
    460 GitHub watchers
    Updated Nov 9, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    Ranks #9 among AI repositories ranked this week, and #5 over the last 30 days; #50 of 170 repositories with measured growth this week (top 29%).

    This week's +1,568 stars is below its 30-day pace of about +2,599 per week.

    5 releases in the last 90 days, the latest 5 days ago, with 31 contributors on GitHub.

    The biggest single-day gain in the last year, +1,160 stars on Sep 28, coincided with release v2026.10.

    Use Cases & Benefits

    • Provides a comprehensive, from-scratch AI engineering curriculum covering math, machine learning, deep learning, NLP, computer vision, agents, and production systems.
    • Delivers a linear, hands-on learning path with 503 lessons and 20 phases, building AI concepts from raw math to deployable artifacts in multiple languages.
    • Use for mastering foundational AI math and algorithms by implementing them manually before using frameworks like PyTorch or JAX.
    • Use for developing practical skills in building and deploying autonomous AI agents and multi-agent systems with reusable code and prompts.
    • Use for educators and learners seeking a structured, open-source AI course that bridges theory and production with real coding projects.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    MIT

    Permissive: commercial use, modification and redistribution are allowed with attribution.

    Community files

    • README: present
    • Contributing guide: present
    • Code of conduct: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    84% of students already use AI tools. Only 18% feel prepared to use them professionally. This curriculum closes that gap.

    503 lessons. 20 phases. ~320 hours. Python, TypeScript, Rust, Julia. Every lesson ships a reusable artifact: a prompt, a skill, an agent, an MCP server. Free, open source, MIT.

    You don't just learn AI. You build it. End-to-end. By hand.

    150,639 readers  ·  241,669 page views in the last 30 days  ·  as of 2026-06-07

    Most AI material teaches in scattered pieces. A paper here, a fine-tuning post there, a flashy agent demo somewhere else. The pieces rarely line up. You ship a chatbot but can't explain its loss curve. You hook a function to an agent but can't say what attention does inside the model that's calling it.

    This curriculum is the spine. 20 phases, 503 lessons, four languages: Python, TypeScript, Rust, Julia. Linear algebra at one end, autonomous swarms at the other. Every algorithm gets built from raw math first. Backprop. Tokenizer. Attention. Agent loop. By the time PyTorch shows up, you already know what it's doing under the hood.

    Each lesson runs the same loop: read the problem, derive the math, write the code, run the test, keep the artifact. No five-minute videos, no copy-paste deploys, no hand-holding. Free, open source, and built to run on your own laptop.

    Twenty phases stack on top of each other. Math is the floor. Agents and production are the roof. Skip ahead if you already know the lower layers, but don't skip and then wonder why something at the top is breaking.

    Excerpt from the rohitg00/ai-engineering-from-scratch README on GitHub (MIT license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Aug 27: +596Aug 28: +475Aug 29: +326Aug 30: +305Aug 31: +320Sep 1: +250Sep 2: +254Sep 3: +205Sep 4: +86Sep 9: +425Sep 10: +562Sep 11: +128Sep 12: +119Sep 13: +73Sep 14: +124Sep 15: +137Sep 16: +98Sep 17: +95Sep 18: +82Sep 19: +54Sep 20: +64Sep 21: +71Sep 22: +33Sep 25: +1,028Sep 26: +871Sep 27: +857Sep 28: +1,160Oct 2: +290Oct 3: +384Oct 4: +777Oct 5: +839Oct 6: +575Oct 7: +320Oct 8: +281Oct 9: +339Oct 10: +525Oct 11: +671Oct 12: +310Oct 13: +449Oct 14: +570Oct 15: +460Oct 16: +642Oct 17: +526Oct 18: +377Oct 19: +366Oct 20: +400Oct 21: +345Oct 22: +314Oct 23: +380Oct 24: +326Oct 25: +500Oct 26: +508Oct 27: +546Oct 28: +331Oct 29: +628Oct 30: +270Oct 31: +148Nov 1: +353Nov 2: +152

    +31,188 stars over 88 days across 65 snapshot days; best day +1,160 on Sep 28.

    Forks

    13.8K+5.7K

    Open issues

    59-47

    Compared with peers in AI

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth

    View category →
    rohitg00/ai-engineering-from-scratch compared with AI repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    D4Vinci/Scrapling99.9K+8.1K654 days ago
    thedotmack/claude-mem114.9K+5.6K35today
    calesthio/OpenMontage78.3K+4.3K40—
    heygen-com/hyperframes81.1K+4.0K45today
    harry0703/MoneyPrinterTurbo141.1K+3.8K552 days ago
    rohitg00/ai-engineering-from-scratch77.8K+1.6K655 days ago
    Category median99.9K+4.3K45—
    Compare ai-engineering-from-scratch with Scrapling, claude-mem, OpenMontage →

    Also by rohitg00

    Other repositories from this maintainer that GStars tracks

    Discover Repositories

    Search across tracked repositories by name or description