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.

#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