Google AI Edge Gallery
Run small language models locally on phones and computers
Python-like language with C-level performance for AI code
The Modular platform, which includes the MAX inference stack and the Mojo programming language, designed to give Python-like readability and flexibility with performance closer to C and C++. It is for developers writing performance-sensitive AI and data-processing code, including code generated by LLMs.
Mojo is a compiled language with Python-flavored syntax and modern memory/ownership features; the modular repository ships the language toolchain plus the MAX engine for running models, so you can write hot paths in Mojo and integrate them with existing Python-style workflows.
Top 10 Repos: 2,282 Claude plugins, free codex, & 8 more.
Top 10 GitHub: AI videos, gorgeous diagrams, token savings and more
Run small language models locally on phones and computers
Tiny special-purpose models that run locally on everyday devices
Lightweight coding-agent harness for running many agents locally
Build a ChatGPT-like LLM in PyTorch step by step
Train a tiny language model from scratch on regular hardware
Learn to build, deploy and iterate production ML apps