#large-language-models

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

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

Ongoing research training transformer models at scale

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

Scalable data pre processing and curation toolkit for LLMs

Observal is self-hosted registry for your coding agent extensions with a built in insight engine. Setup Observal, define the scope and share your Skills, MCPs and Agents with your peers.

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

Redis Vector Library (RedisVL) -- the AI-native Python client for Redis.

[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation

Build and run agents you can see, understand and trust.

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

Efficient in-memory representation for ONNX, in Python

Evaluate and improve models and agents using environments

Lightweight and portable LLM sandbox runtime (code interpreter) Python library.

Custom AI agent platform to speed up your work.

🚀 Efficient implementations for emerging model architectures

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Chronos: Pretrained Models for Time Series Forecasting

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Fast, Flexible and Portable Structured Generation

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows