The LLM Evaluation Framework

An end to end demo of Google's Cloud data and analytic stack.

The LLM Red Teaming Framework

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Latitude is the open-source prompt engineering platform to build, evaluate, and refine your prompts with AI

This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for re…

An AI Hedge Fund Team

the LLM vulnerability scanner

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.

VibeOps - Cisco pyATS MCP Plus Many Other MCPs

Build effective agents using Model Context Protocol and simple workflow patterns

⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients.

🚀 The fast, Pythonic way to build MCP servers and clients

A helper SDK to wrap the Google SecOps API for common security use cases

Python A2A is a powerful, easy-to-use library for implementing Google's [Agent-to-Agent (A2A) protocol](https://google.github.io/A2A/). It enables seamless communication between AI agents, creating…

A lightweight, powerful framework for multi-agent workflows

Agno is a lightweight library for building Agents with memory, knowledge, tools and reasoning.

Open-source observability for your LLM application, based on OpenTelemetry

An encyclopedia of jailbreaking techniques to make AI models safer.

A collection of examples and tutorials for Qdrant vector search engine

Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with comma…

Protection against Model Serialization Attacks

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

Multi-Agent Systems with Google's Agent Development Kit + A2A + MCP

The Security Toolkit for LLM Interactions

Azure Open AI (demos, documentation, accelerators).