Build Multimodal AI Agents with memory, knowledge and tools. Simple, fast and model-agnostic.

Additional packages (components, document stores and the likes) to extend the capabilities of Haystack

A collection of sample agents built with Agent Development (ADK)

Examples and guides for using the Gemini API

Memory for AI Agents in 6 lines of code

Extremely fast Query Engine for DataFrames, written in Rust

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

LLM agents built for control. Designed for real-world use. Deployed in minutes.

A collection of guides and examples for the Gemma open models from Google.

Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.

PyTorch native quantization and sparsity for training and inference

Public repository for Skills

The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)

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

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

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

Nixopus streamlines your entire server workflow - ServerOps with no fuss

Development repository for the Triton language and compiler