--- title: "picoGPT vs ai-engineering-from-scratch" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/jaymody-picogpt-vs-rohitg00-ai-engineering-from-scratch" tools: ["jaymody-picogpt", "rohitg00-ai-engineering-from-scratch"] --- # picoGPT vs ai-engineering-from-scratch *GraphCanon updated Sep 20, 2026* ## Verdict Pick picoGPT if `picoGPT` is a minimal and extremely compact GPT-2 model, written in NumPy for the sake of readability despite significant inefficiencies; pick ai-engineering-from-scratch if ai-engineering-from-scratch is a comprehensive course that teaches AI engineering skills from foundational math to advanced AI agents and machine learning techniques, using Python and Node.js for interactive learning and. [picoGPT](https://github.com/jaymody/picoGPT) reports 3.5k GitHub stars, 456 forks, and 14 open issues, last pushed Apr 24, 2023. [ai-engineering-from-scratch](https://aiengineeringfromscratch.com) has 55k stars, 9.6k forks, and 114 open issues, last pushed Sep 7, 2026. Figures are from public GitHub metadata via [picoGPT's repository](https://github.com/jaymody/picoGPT) and [ai-engineering-from-scratch's repository](https://github.com/rohitg00/ai-engineering-from-scratch). | | [picoGPT](/tools/jaymody-picogpt.md) | [ai-engineering-from-scratch](/tools/rohitg00-ai-engineering-from-scratch.md) | | --- | --- | --- | | Tagline | An unnecessarily tiny implementation of GPT-2 in NumPy | Learn, build, and deploy AI engineering skills from scratch. | | Stars | 3,470 | 54,935 | | Forks | 456 | 9,649 | | Open issues | 14 | 114 | | Language | Python | Python | | Adopt for | `picoGPT` is a minimal and extremely compact GPT-2 model, written in NumPy for the sake of readability despite significant inefficiencies. | ai-engineering-from-scratch is a comprehensive course that teaches AI engineering skills from foundational math to advanced AI agents and machine learning techniques, using Python and Node.js for interactive learning and | | Persona | - | - | | Runtime | - | - | | License | `MIT License` - A permissive license enabling free modification and distribution even in commercial software. | MIT | | Categories | Model Training | AI Agents, Computer Vision, Developer Tools, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [picoGPT](/tools/jaymody-picogpt.md) | [ai-engineering-from-scratch](/tools/rohitg00-ai-engineering-from-scratch.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Active (82%) | | Days since push | 1211d | 10d | | Open issues (now) | 14 | 114 | | Stars delta | +3 (30d) | +8.1k (30d) | | Open issues delta | 0 (30d) | +7 (30d) | | Full report | [trust report](/tools/jaymody-picogpt/trust.md) | [trust report](/tools/rohitg00-ai-engineering-from-scratch/trust.md) | ## Shared compatibility - **Python**: [picoGPT](/tools/jaymody-picogpt.md) - Python runtime; [ai-engineering-from-scratch](/tools/rohitg00-ai-engineering-from-scratch.md) - Python runtime ## Decision facts: picoGPT - **Requirements:** Min 2 GB RAM; PicoGPT may struggle with larger datasets due to its inefficiencies, despite being minimal. - **Adopt for:** `picoGPT` is a minimal and extremely compact GPT-2 model, written in NumPy for the sake of readability despite significant inefficiencies. - **License detail:** `MIT License` - A permissive license enabling free modification and distribution even in commercial software. ## Decision facts: ai-engineering-from-scratch - **Adopt for:** ai-engineering-from-scratch is a comprehensive course that teaches AI engineering skills from foundational math to advanced AI agents and machine learning techniques, using Python and Node.js for interactive learning and ## Choose when ### Choose picoGPT if… - Requirements: Min 2 GB RAM; PicoGPT may struggle with larger datasets due to its inefficiencies, despite being minimal.. - Tags unique to picoGPT: gpt, gpt-2, large-language-models, neural-network. - - Use `picoGPT` when you need an example to understand GPT-2's functioning at its most pared-down level. ### Choose ai-engineering-from-scratch if… - Tags unique to ai-engineering-from-scratch: agents, ai-engineering, computer-vision, from-scratch. - Also covers AI Agents, Computer Vision, Developer Tools. - when you need a structured course that covers a wide range of AI engineering topics from scratch, including foundational math, deep learning, and reinforcement learning. ## When NOT to use picoGPT - - Avoid `picoGPT` in scenarios requiring efficient batch processing or advanced generation techniques like top-p sampling, as it lacks these features. - - Do not use `picoGPT` if speed and scalability are critical for your project, given its megaSlow execution. ## When NOT to use ai-engineering-from-scratch - if you are looking for a tool that focuses solely on theoretical knowledge without practical application, as this course emphasizes hands-on learning. - when you do not have access to Node.js or Python, as these are required for running the course and its interactive components. - if you prefer a more traditional learning approach without the use of terminal-based learning tools, as the course is designed for interactive terminal sessions. - when you are working with a development environment that does not support skill-capable hosts, as the course is optimized for such environments. ## Common questions ### What is the difference between picoGPT and ai-engineering-from-scratch? picoGPT: An unnecessarily tiny implementation of GPT-2 in NumPy. ai-engineering-from-scratch: Learn, build, and deploy AI engineering skills from scratch.. See the comparison table for live GitHub stats and shared categories. ### When should I choose picoGPT over ai-engineering-from-scratch? Choose picoGPT over ai-engineering-from-scratch when Requirements: Min 2 GB RAM; PicoGPT may struggle with larger datasets due to its inefficiencies, despite being minimal.; Tags unique to picoGPT: gpt, gpt-2, large-language-models, neural-network; - Use `picoGPT` when you need an example to understand GPT-2's functioning at its most pared-down level. ### When should I choose ai-engineering-from-scratch over picoGPT? Choose ai-engineering-from-scratch over picoGPT when Tags unique to ai-engineering-from-scratch: agents, ai-engineering, computer-vision, from-scratch; Also covers AI Agents, Computer Vision, Developer Tools; when you need a structured course that covers a wide range of AI engineering topics from scratch, including foundational math, deep learning, and reinforcement learning. ### When should I avoid picoGPT? - Avoid `picoGPT` in scenarios requiring efficient batch processing or advanced generation techniques like top-p sampling, as it lacks these features. - Do not use `picoGPT` if speed and scalability are critical for your project, given its megaSlow execution. ### When should I avoid ai-engineering-from-scratch? if you are looking for a tool that focuses solely on theoretical knowledge without practical application, as this course emphasizes hands-on learning. when you do not have access to Node.js or Python, as these are required for running the course and its interactive components. if you prefer a more traditional learning approach without the use of terminal-based learning tools, as the course is designed for interactive terminal sessions. when you are working with a development environment that does not support skill-capable hosts, as the course is optimized for such environments. ### Is picoGPT or ai-engineering-from-scratch more popular on GitHub? ai-engineering-from-scratch has more GitHub stars (54,935 vs 3,470). Stars measure visibility, not whether either tool fits your constraints. ### Are picoGPT and ai-engineering-from-scratch open source? Yes - both are open-source projects on GitHub (picoGPT: MIT, ai-engineering-from-scratch: MIT). ### Where can I find alternatives to picoGPT or ai-engineering-from-scratch? GraphCanon lists graph-backed alternatives at [picoGPT alternatives](/tools/jaymody-picogpt/alternatives) and [ai-engineering-from-scratch alternatives](/tools/rohitg00-ai-engineering-from-scratch/alternatives) ([picoGPT markdown twin](/tools/jaymody-picogpt/alternatives.md), [ai-engineering-from-scratch markdown twin](/tools/rohitg00-ai-engineering-from-scratch/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/jaymody-picogpt-vs-rohitg00-ai-engineering-from-scratch.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, picoGPT or ai-engineering-from-scratch? picoGPT: Dormant. ai-engineering-from-scratch: Active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for picoGPT and ai-engineering-from-scratch? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [picoGPT trust report](/tools/jaymody-picogpt/trust); [ai-engineering-from-scratch trust report](/tools/rohitg00-ai-engineering-from-scratch/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=jaymody-picogpt`](/api/graphcanon/graph?tool=jaymody-picogpt) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_