Llama is Meta’s repository with inference code for earlier Llama models and links to newer family repositories.
Open Source: #ai
Catalog projects marked with #ai. Tags work as dedicated landing pages, so related tools are easier to find and connect.
This collection holds 142 projects with a combined 11,881,711 GitHub stars. Main languages: Python, TypeScript, Rust.
About the AI projects here
Artificial intelligence is the fastest-growing corner of open source: the last couple of years brought thousands of GitHub tools around neural networks, from ready-made assistants to low-level inference engines. This page collects the ones genuinely worth opening: alive communities, clear docs, practical value.
Inside you will find frameworks for working with language models, agent systems, local-inference tools, and learning resources. Every project card shows stars, the license, and a human description so you can judge fit quickly.
Repositories
AutoGen is Microsoft’s Python framework for multi-agent AI applications; the project is now in maintenance mode.
LLM App is a set of Pathway templates for RAG, document search, and AI pipelines with live data.
GPT-SoVITS is a project for few-shot speech synthesis and voice transfer from small audio samples.
Ultralytics is a Python package and CLI for YOLO models and computer-vision tasks.
Context7 is a platform and MCP server that supplies up-to-date documentation to AI editors and agent tools.
PrivateGPT is a project for working with documents through language models without sending data outside.
OpenSpec is a TypeScript tool for spec-driven development in AI coding assistants.
face_recognition is a Python library and command-line tool for face recognition, built on top of dlib.
nanochat is Andrej Karpathy’s educational project for walking through the main stages of training a small language model and running a simple chat.
gpt-engineer is an experimental command-line platform for generating and changing code from natural-language software descriptions.
CrewAI is a Python framework for building multi-agent AI systems with roles, tasks, and collaborative execution.