Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
GitHub repository with 97,054 stars and 14,849 forks.
Language: Jupyter Notebook
Topics: gpt, large-language-models, llm, python, pytorch, ai, artificial-intelligence, language-model, deep-learning, machine-learning
2026-06-13: 97,054 stars and 14,849 forks.
A hands-on course for building modern LLMs from scratch in PyTorch, with 26 runnable Jupyter Notebooks covering tokenizers, attention, MoE, RLHF, inference, evaluation, and distillation.
GitHub repository with 68 stars and 13 forks.
Trending score: 1.73; stars gained: +5; forks gained: +1.
Language: Jupyter Notebook
Topics: ai, attention, finetune, gpt, large-language-models, llm
Jupyter Notebook notes on Andrej Karpathy's videos and the tutorial series, "Neural Networks: Zero to Hero."
GitHub repository with 231 stars and 39 forks.
Trending score: 1.23; stars gained: +4; forks gained: +2.
Language: Jupyter Notebook
Topics: gpt, neural-networks, nn-zero-to-hero, deep-learning, nlp, pytorch
Generating and validating natural-language explanations for the brain.
GitHub repository with 65 stars and 10 forks.
Trending score: 0.04; stars gained: +0; forks gained: +0.
Language: Jupyter Notebook
Topics: artificial-intelligence, explanation, gpt, gpt4, interpretability, language-model
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
GitHub repository with 10,220 stars and 666 forks.
Trending score: 4.25; stars gained: +180; forks gained: +15.
Language: Jupyter Notebook
LLM Zoomcamp - a free online course about real-life applications of LLMs. In 10 weeks you will learn how to build an AI system that answers questions about your knowledge base.
GitHub repository with 6,342 stars and 1,128 forks.
Trending score: 3.79; stars gained: +50; forks gained: +8.
Language: Jupyter Notebook
Reference PyTorch implementation and models for DINOv3
GitHub repository with 10,678 stars and 876 forks.
Trending score: 3.14; stars gained: +70; forks gained: +6.
Language: Jupyter Notebook
Implement a reasoning LLM in PyTorch from scratch, step by step
GitHub repository with 4,504 stars and 662 forks.
Trending score: 2.79; stars gained: +24; forks gained: +1.
Language: Jupyter Notebook
Topics: ai, artificial-intelligence, deep-learning, large-language-models, llms, machine-learning
Examples and guides for using the OpenAI API
GitHub repository with 74,165 stars and 12,554 forks.
Trending score: 2.74; stars gained: +17; forks gained: +5.
Language: Jupyter Notebook
Topics: openai, chatgpt, gpt-4, openai-api
Optimize prompts, code, and more with AI-powered Reflective Text Evolution
GitHub repository with 5,146 stars and 431 forks.
Trending score: 2.72; stars gained: +18; forks gained: +6.
Language: Jupyter Notebook
🙌 OpenHands: AI-Driven Development
GitHub repository with 77,159 stars and 9,800 forks.
Trending score: 4.87; stars gained: +393; forks gained: +43.
Language: Python
Topics: agent, artificial-intelligence, chatgpt, claude-ai, cli, developer-tools
Production-ready platform for agentic workflow development.
GitHub repository with 145,307 stars and 22,855 forks.
Trending score: 4.58; stars gained: +200; forks gained: +26.
Language: TypeScript
Topics: agent, agentic-ai, agentic-framework, agentic-workflow, ai, automation
A high-throughput and memory-efficient inference and serving engine for LLMs
GitHub repository with 82,924 stars and 18,082 forks.
Trending score: 4.18; stars gained: +80; forks gained: +23.
Language: Python
Topics: amd, blackwell, cuda, deepseek, deepseek-v3, gpt
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
GitHub repository with 34,699 stars and 2,392 forks.
Trending score: 3.92; stars gained: +79; forks gained: +15.
Language: Python
Topics: agent, ai, chatbot, chatgpt, discord, docker
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
GitHub repository with 78,688 stars and 15,431 forks.
Trending score: 3.82; stars gained: +87; forks gained: +7.
Language: TypeScript
Topics: agent, agent-collaboration, agent-harness, ai, cao, chatgpt
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
GitHub repository with 12,115 stars and 1,112 forks.
Trending score: 3.76; stars gained: +69; forks gained: +6.
Language: Python
Topics: ai-research, autonomous-agent, claude-code, codex, mcp, ml-research