Roberto Carratalá

One AI API to Power Them All

Stop wrestling with fragmented AI tools. Go from local development to a production cluster with one unified API for inference, RAG, and agents.

One AI API to Power Them All
#1about 5 minutes

The challenge of building production-ready AI applications

The current AI landscape is fragmented with many tools, making it complex to build, scale, and maintain applications with features like RAG and agents.

#2about 3 minutes

Introducing Llama Stack for a unified AI API

Llama Stack, an open-source project from Meta, provides a standardized, modular framework to simplify AI development with a single API for various components.

#3about 3 minutes

Standardizing model inference and safety guardrails

Llama Stack abstracts away differences between local and remote LLMs and integrates safety shields to filter harmful inputs and outputs.

#4about 2 minutes

Simplifying retrieval-augmented generation (RAG) pipelines

Llama Stack organizes the complex RAG process into three distinct, swappable layers for vector embeddings, retrieval, and agentic workflows.

#5about 4 minutes

Building AI agents using the Model Context Protocol

Llama Stack simplifies agent creation by integrating tools, orchestration, and reasoning models through the standardized Model Context Protocol (MCP).

#6about 3 minutes

Gaining application observability with built-in telemetry

Llama Stack provides out-of-the-box telemetry using OpenTelemetry, enabling developers to trace multi-step agent workflows with tools like Jaeger.

#7about 4 minutes

A local demo of inference, safety, and agents

This live demo showcases running Llama Stack locally to perform inference, block unsafe prompts, use an agent to check the weather, and inspect traces in Jaeger.

#8about 1 minute

Transitioning AI applications from local to production

Llama Stack enables a seamless transition from a local development setup to a scalable production environment on Kubernetes by maintaining a consistent API.

#9about 5 minutes

A production demo of a multi-agent business workflow

A complex agent interacts with multiple MCP servers to query a CRM, analyze customer data, send Slack notifications, and generate a PDF report.

Related jobs
Jobs that call for the skills explored in this talk.

Matching moments

Comparing open source tools for serving LLMs
02:48 MIN

Comparing open source tools for serving LLMs

Self-Hosted LLMs: From Zero to Inference

Introducing RAGStack as an opinionated development framework
01:47 MIN

Introducing RAGStack as an opinionated development framework

Accelerating GenAI Development: Harnessing Astra DB Vector Store and Langflow for LLM-Powered Apps

Integrating decentralized tech and AI into your stack
02:35 MIN

Integrating decentralized tech and AI into your stack

End-to-End TypeScript: Completing the Modern Development Stack

Three pillars for integrating LLMs in products
01:47 MIN

Three pillars for integrating LLMs in products

Using LLMs in your Product

Testing Spring AI applications with local LLMs
04:01 MIN

Testing Spring AI applications with local LLMs

What's (new) with Spring Boot and Containers?

Understanding the modern LLM application stack
02:08 MIN

Understanding the modern LLM application stack

Building AI Applications with LangChain and Node.js

The opaque and complex stack of modern LLM services
02:19 MIN

The opaque and complex stack of modern LLM services

You are not my model anymore - understanding LLM model behavior

Using Red Hat tools across the AI development lifecycle
01:51 MIN

Using Red Hat tools across the AI development lifecycle

Developer Experience, Platform Engineering and AI powered Apps

Featured Partners

Related Videos

See all videos
Self-Hosted LLMs: From Zero to Inference30:04

Self-Hosted LLMs: From Zero to Inference

Roberto Carratalá & Cedric Clyburn

The State of GenAI & Machine Learning in 202526:47

The State of GenAI & Machine Learning in 2025

Alejandro Saucedo

DevOps for AI: running LLMs in production with Kubernetes and KubeFlow34:21

DevOps for AI: running LLMs in production with Kubernetes and KubeFlow

Aarno Aukia

Agentic AI Systems for Critical Workloads30:01

Agentic AI Systems for Critical Workloads

Mario Fusco

Enterprise Integration Is Dead! Long Live AI-Driven Integration with Apache Camel32:24

Enterprise Integration Is Dead! Long Live AI-Driven Integration with Apache Camel

Bruno Meseguer & Markus Eisele

Azure AI Foundry for Developers: Open Tools, Scalable Agents, Real Impact23:33

Azure AI Foundry for Developers: Open Tools, Scalable Agents, Real Impact

Oliver Will

New AI-Centric SDLC: Rethinking Software Development with Knowledge Graphs15:26

New AI-Centric SDLC: Rethinking Software Development with Knowledge Graphs

Gregor Schumacher, Sujay Joshy & Marcel Gocke

Java Meets AI: Empowering Spring Developers to Build Intelligent Apps31:53

Java Meets AI: Empowering Spring Developers to Build Intelligent Apps

Timo Salm

Related Articles

View all articles
CH
Chris Heilmann
With AIs wide open - WeAreDevelopers at All Things Open 2025
Last week our VP of Developer Relations, Chris Heilmann, flew to Raleigh, North Carolina to present at All Things Open . An excellent event he had spoken at a few times in the past and this being the “Lucky 13” edition, he didn’t hesitate to come and...
With AIs wide open - WeAreDevelopers at All Things Open 2025
DC
Daniel Cranney
Dev Digest 196: AI Killed DevOps, LLM Political Bias & AI Security
Inside last week’s Dev Digest 196 . ⚖️ Political bias in LLMs 🫣 AI written code causes 1 in 5 security breaches 🖼️ Is there a limit to alternative text on images? 📝 CodeWiki - understand code better 🟨 Long tasks in JavaScript 👻 Scare yourself into n...
Dev Digest 196: AI Killed DevOps, LLM Political Bias & AI Security

From learning to earning

Jobs that call for the skills explored in this talk.