meta-llama/llama
Llama
Llama is Meta’s repository with inference code for earlier Llama models and links to newer family repositories.
Open Source: #llm
Catalog projects marked with #llm. Tags work as dedicated landing pages, so related tools are easier to find and connect.
This collection holds 55 projects with a combined 4,548,466 GitHub stars. Main languages: Python, TypeScript, Go.
About the LLM tools
Large language models stopped being research-lab magic — people now run them locally, fine-tune them on their data, and ship them inside products. The open source ecosystem around LLMs moves faster than any other: new tools land literally every week.
This collection covers inference engines, RAG and agent frameworks, API wrappers, and local runners. If you are building on top of language models, start here: these are proven projects under active development.
Repositories
Found: 55
karpathy/nanochat
nanochat
nanochat is Andrej Karpathy’s educational project for walking through the main stages of training a small language model and running a simple chat.
jingyaogong/minimind
MiniMind
MiniMind is an educational PyTorch project for reproducing a small language model end to end: data, pretraining, finetuning, and experiments.
BerriAI/litellm
LiteLLM
LiteLLM is a Python SDK and proxy for calling many LLM providers through one interface.
run-llama/llama_index
LlamaIndex
LlamaIndex is a framework for connecting LLM applications to external data, indexes, and tools.
oobabooga/textgen
TextGen
TextGen is a desktop app and web interface for local LLMs: chat, generation, vision, tool-calling, and compatible APIs.
mudler/LocalAI
LocalAI
LocalAI is an open AI engine for running LLM, vision, voice, image, and video models through compatible APIs on your own hardware.
CherryHQ/cherry-studio
Cherry Studio
Cherry Studio is a desktop AI client for multiple LLM providers, assistants, documents, MCP, and local models.
Lordog/dive-into-llms
Dive into LLMs
Dive into LLMs is a practical learning course on large language models.
