Stars
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A high-throughput and memory-efficient inference and serving engine for LLMs
Interact with your documents using the power of GPT, 100% privately, no data leaks
LlamaIndex is the leading framework for building LLM-powered agents over your data.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
State-of-the-art 2D and 3D Face Analysis Project
Fully open reproduction of DeepSeek-R1
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Turns Data and AI algorithms into production-ready web applications in no time.
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
Janus-Series: Unified Multimodal Understanding and Generation Models
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
Refine high-quality datasets and visual AI models
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
ImageBind One Embedding Space to Bind Them All
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
Modeling, training, eval, and inference code for OLMo
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
Universal and Transferable Attacks on Aligned Language Models