A high-throughput and memory-efficient inference and serving engine for LLMs

Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one

A collection of full time roles in SWE, Quant, and PM for new grads.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

Empowering everyone to build reliable and efficient software.

A JAX-native LLM Post-Training Library

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

🐻 Bear necessities for state management in React

Open Source framework for voice and multimodal conversational AI

τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Knowledge Graph Generation from Any Text

End-to-end realtime stack for connecting humans and AI

LlamaIndex is the leading framework for building LLM-powered agents over your data.

Inference-time scaling for LLMs-as-a-judge.

Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.

[SIGMOD 2026] F3: The Open-Source Data File Format for the Future

Sandbox for developing and testing UI components in isolation

A programming framework for agentic AI

A library to generate LaTeX expression from Python code.

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Open-Source Implementations of Multi-Modal Diffusion Models Optimized for Highest Quality and Ease of Use

Examples on how to use LangChain and Ray

Ensembling Hugging Face transformers made easy