Comparison
LLMs-from-scratch vs ai-engineering-from-scratch
LLMs-from-scratch (Implement a ChatGPT-like LLM in PyTorch from scratch, step by step) vs ai-engineering-from-scratch (Learn it. Build it. Ship it for others.) - live GitHub stats and typed graph relationships, not marketing.
Markdown twin · LLMs-from-scratch alternatives · ai-engineering-from-scratch alternatives
GraphCanon updated today
vs
Tagline
- LLMs-from-scratch
- Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
- ai-engineering-from-scratch
- Learn it. Build it. Ship it for others.
Stars
- LLMs-from-scratch
- 99k
- ai-engineering-from-scratch
- 38k
Forks
- LLMs-from-scratch
- 15k
- ai-engineering-from-scratch
- 6.3k
Open issues
- LLMs-from-scratch
- 4
- ai-engineering-from-scratch
- 95
Language
- LLMs-from-scratch
- Jupyter Notebook
- ai-engineering-from-scratch
- Python
Adopt for
- LLMs-from-scratch
- LLMs-from-scratch is a repository that offers detailed, step-by-step guidance on developing, pretraining, and finetuning GPT-like large language models using PyTorch. The codebase complements a book dedicated to building
- ai-engineering-from-scratch
- A comprehensive curriculum for AI engineering that focuses on building reusable artifacts using Python, TypeScript, Rust, and Julia.
Persona
- LLMs-from-scratch
- -
- ai-engineering-from-scratch
- -
Runtime
- LLMs-from-scratch
- -
- ai-engineering-from-scratch
- -
License
- LLMs-from-scratch
- Other
- ai-engineering-from-scratch
- MIT License, allowing free use and distribution for both personal and commercial purposes.
Last pushed
- LLMs-from-scratch
- Jun 2, 2026
- ai-engineering-from-scratch
- Jun 25, 2026
Categories
- LLMs-from-scratch
- LLM Frameworks, Model Training
- ai-engineering-from-scratch
- Evaluation & Observability, Developer Tools, AI Agents, Data & Retrieval, Model Training, Computer Vision
Trust and health
Maintenance
- LLMs-from-scratch
- Steady (60%)
- ai-engineering-from-scratch
- Active (82%)
Days since push
- LLMs-from-scratch
- 35d
- ai-engineering-from-scratch
- 12d
Open issues (now)
- LLMs-from-scratch
- 4
- ai-engineering-from-scratch
- 95
Security scan
- LLMs-from-scratch
- 34 low (34 low)
- ai-engineering-from-scratch
- 83 low (83 low)
Full report
- LLMs-from-scratch
- Trust report
- ai-engineering-from-scratch
- Trust report
Typed relationship
LLMs-from-scratch alternative ai-engineering-from-scratch'ai-engineering-from-scratch' and 'LLMs-from-scratch' both aim at teaching how to build AI models from scratch, though they have a focus on different sets of tools or methods.
Shared compatibility
- Python · LLMs-from-scratch: Python runtime · ai-engineering-from-scratch: Python runtime
Choose LLMs-from-scratch if…
- LLMs-from-scratch is primarily Jupyter Notebook; ai-engineering-from-scratch is Python.
- License: LLMs-from-scratch is Other, ai-engineering-from-scratch is MIT.
- Requirements: Min 8 GB RAM; The repository includes comprehensive documentation that can be used alongside the book 'Build a Large Language Model (From Scratch)' for additional context and.
- 'ai-engineering-from-scratch' and 'LLMs-from-scratch' both aim at teaching how to build AI models from scratch, though they have a focus on different sets of tools or methods.
- Tags unique to LLMs-from-scratch: ai, artificial-intelligence, instruction-tuning, attention-mechanism.
- Also covers LLM Frameworks.
- When you need detailed, step-by-step explanations and examples for constructing an LLM from scratch with PyTorch.
When NOT to use LLMs-from-scratch
- When you are looking for a quick setup or already have familiarity with LLMs as the repository emphasizes building from scratch, which can be time-consuming.
- If your primary goal is production-scale deployment rather than educational understanding, as this tool focuses more on learning through thoroughness rather than speed and optimization.
- For users who prefer not to use specific frameworks like PyTorch and are interested in developing models with other libraries.
Choose ai-engineering-from-scratch if…
- ai-engineering-from-scratch is primarily Python; LLMs-from-scratch is Jupyter Notebook.
- License: ai-engineering-from-scratch is MIT, LLMs-from-scratch is Other.
- Pricing: Open source under MIT license; no costs associated with accessing the curriculum materials, though support might be available on a paid basis..
- Requirements: Min 4 GB RAM.
- 'ai-engineering-from-scratch' and 'LLMs-from-scratch' both aim at teaching how to build AI models from scratch, though they have a focus on different sets of tools or methods.
- Tags unique to ai-engineering-from-scratch: ai-engineering, agents, llm, course.
- Also covers Evaluation & Observability, Developer Tools, AI Agents, Data & Retrieval, Computer Vision.
- When you want to gain a deep understanding of how AI models work from scratch before moving onto frameworks like PyTorch or TensorFlow.
When NOT to use ai-engineering-from-scratch
- If you are looking for a quick, high-level overview of how to use AI tools without getting into the underlying math and code.
- This tool might not be suitable if your goal is to rapidly deploy an AI solution using pre-built libraries or frameworks with minimal coding effort.
Explore
LLMs-from-scratch trust report →ai-engineering-from-scratch trust report →LLM Frameworks category →Model Training category →Evaluation & Observability category →Developer Tools category →AI Agents category →Data & Retrieval category →Computer Vision category →All comparisonsStack workflowsTrending tools
Related comparisons
Common questions
- What is the difference between LLMs-from-scratch and ai-engineering-from-scratch?
- LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. ai-engineering-from-scratch: Learn it. Build it. Ship it for others.. See the comparison table for live GitHub stats and shared categories.
- When should I choose LLMs-from-scratch over ai-engineering-from-scratch?
- Choose LLMs-from-scratch over ai-engineering-from-scratch when LLMs-from-scratch is primarily Jupyter Notebook; ai-engineering-from-scratch is Python; License: LLMs-from-scratch is Other, ai-engineering-from-scratch is MIT; Requirements: Min 8 GB RAM; The repository includes comprehensive documentation that can be used alongside the book 'Build a Large Language Model (From Scratch)' for additional context and; 'ai-engineering-from-scratch' and 'LLMs-from-scratch' both aim at teaching how to build AI models from scratch, though they have a focus on different sets of tools or methods; Tags unique to LLMs-from-scratch: ai, artificial-intelligence, instruction-tuning, attention-mechanism; Also covers LLM Frameworks; When you need detailed, step-by-step explanations and examples for constructing an LLM from scratch with PyTorch.
- When should I choose ai-engineering-from-scratch over LLMs-from-scratch?
- Choose ai-engineering-from-scratch over LLMs-from-scratch when ai-engineering-from-scratch is primarily Python; LLMs-from-scratch is Jupyter Notebook; License: ai-engineering-from-scratch is MIT, LLMs-from-scratch is Other; Pricing: Open source under MIT license; no costs associated with accessing the curriculum materials, though support might be available on a paid basis.; Requirements: Min 4 GB RAM; 'ai-engineering-from-scratch' and 'LLMs-from-scratch' both aim at teaching how to build AI models from scratch, though they have a focus on different sets of tools or methods; Tags unique to ai-engineering-from-scratch: ai-engineering, agents, llm, course; Also covers Evaluation & Observability, Developer Tools, AI Agents, Data & Retrieval, Computer Vision; When you want to gain a deep understanding of how AI models work from scratch before moving onto frameworks like PyTorch or TensorFlow.
- When should I avoid LLMs-from-scratch?
- When you are looking for a quick setup or already have familiarity with LLMs as the repository emphasizes building from scratch, which can be time-consuming. If your primary goal is production-scale deployment rather than educational understanding, as this tool focuses more on learning through thoroughness rather than speed and optimization. For users who prefer not to use specific frameworks like PyTorch and are interested in developing models with other libraries.
- When should I avoid ai-engineering-from-scratch?
- If you are looking for a quick, high-level overview of how to use AI tools without getting into the underlying math and code. This tool might not be suitable if your goal is to rapidly deploy an AI solution using pre-built libraries or frameworks with minimal coding effort.
- Is LLMs-from-scratch or ai-engineering-from-scratch more popular on GitHub?
- LLMs-from-scratch has more GitHub stars (98,748 vs 37,611). Stars measure visibility, not whether either tool fits your constraints.
- Are LLMs-from-scratch and ai-engineering-from-scratch open source?
- Yes - both are open-source projects on GitHub (LLMs-from-scratch: Other, ai-engineering-from-scratch: MIT).
- Where can I find alternatives to LLMs-from-scratch or ai-engineering-from-scratch?
- GraphCanon lists graph-backed alternatives at /tools/rasbt-llms-from-scratch/alternatives and /tools/rohitg00-ai-engineering-from-scratch/alternatives (/tools/rasbt-llms-from-scratch/alternatives.md, /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 /compare/rasbt-llms-from-scratch-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, LLMs-from-scratch or ai-engineering-from-scratch?
- LLMs-from-scratch: Steady. 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 LLMs-from-scratch and ai-engineering-from-scratch?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: LLMs-from-scratch: /tools/rasbt-llms-from-scratch/trust; ai-engineering-from-scratch: /tools/rohitg00-ai-engineering-from-scratch/trust.