What is Llama Stack?
Llama Stack is a comprehensive system that provides a uniform set of tools for building, scaling, and deploying generative AI applications, enabling developers to create, integrate, and orchestrate multiple AI services and capabilities into an adaptable setup.
Llama Stack codifies best practices across the Llama ecosystem. With the release of the Llama 4 herd of models, you can use Llama Stack to build innovative, personalized applications with the most accessible and scalable generation of Llama.
Overview
Llama Stack Provides
Flexible Deployment Options
Consistent Application Behavior
Robust Distribution Partner Network
Standardized APIs
Provides consistent interfaces for building and deploying AI applications.
Flexible Deployment Options
Supports local development, cloud, on-premises, and mobile environments.
Pre-built Tools
Offers tools for inference, safety monitoring, and memory management.
Scalable Infrastructure
Facilitates easy scaling of AI applications.
Strong Partner Network
Collaborates with various providers to offer specialized services.
Telemetry and Monitoring
Includes built-in support for tracing requests, evaluating model outputs.Capabilities
Llama Stack SDKs have differentiating features and capabilities that empower developers to create AI applications with ease from RAG to innovative applications tailored for mobile use cases.
RAG
Multi-image inference
Custom tool calling
RAG
RAG
Easily add RAG to your apps with our mobile framework and customize tailored models with user-specific context.
Available in local and remote inference modes. Check out more on GitHub.
Multi-image inference
Multi-image inference
Utilize multi-image inference to build experiences that process and analyze multiple images at once. Available in remote inference mode only. Learn more on GitHub.
Custom tool calling
Custom tool calling
Mobile framework supports unique tool calls like creating a calendar event all within your device’s app. Available in local and remote inference mode. Learn more on GitHub.
RAG
Easily add RAG to your apps with our mobile framework and customize tailored models with user-specific context. Available in local and remote inference modes. Check out more on GitHub.
Our approach
Docs
Need help getting started building on Llama Stack? Check out our documentation.Learn more
Cookbooks
The tools and resources you need to build with Llama Stack. Access prepackaged, verified provider distributions and mobile SDKs with iOS and Android support.Learn more
Llama Stack: a streamlined developer experience
Build faster, deploy anywhere and get the most out of the latest Llama models on day 1.
For developers
Best practices included
Optimized support for agentic tool calling, safety guardrails, inference and much more, significantly lowering development costs.Develop in your preferred language
Choose from python, node, kotlin, and swift programming languages to quickly build
your applications.
your applications.
Choose from python, node, kotlin, and swift programming languages to quickly build your applications.
Develop & deploy anywhere
With a common API, choose any distribution and deploy on-prem, locally hosted, or even on-device at the edge.
For partners & distributors
A standard API
Requires fewer model level changes across versions accelerating time to market for new models and lowering engineering investment.Interoperability with the ecosystem
Leverage the fast moving Llama ecosystem by building on a common API and incorporate new components faster.Support for agentic components
Llama Stack releases natively support tool calling, safety guardrails, retrieval augmented generation, an inference loop and other agentic functionality.
Llama Stack releases natively support tool calling, safety guardrails, retrieval augmented generation, an inference loop and other agentic functionality.
For developers
For developers
Best practices included
Optimized support for agentic tool calling, safety guardrails, inference and much more, significantly lowering development costs.Develop in your preferred language
Choose from python, node, kotlin, and swift programming languages to quickly build your applications.Develop & deploy anywhere
With a common API, choose any distribution and deploy on-prem, locally hosted, or even on-device at the edge.For Partners & Distributors
For Partners & Distributors
A standard API
Requires fewer model level changes across versions accelerating time to market for new models and lowering engineering investment.Interoperability with the ecosystem
Leverage the fast moving Llama ecosystem by building on a common API and incorporate new components faster.Support for agentic components
Llama Stack releases natively support tool calling, safety guardrails, retrieval augmented generation, an inference loop and other agentic functionality.Our partner ecosystem
Llama Protections
Making safety tools accessible to everyone. Enabling developers, advancing safety, and building an open ecosystem.Learn more
Llama Stack resources
Introduction to Llama Stack
Learn about Llama Stack from Dalton Flanagan Meta’s Software engineering working on AI.
Learn more
Building Agents with Llama Stack
This technical tutorial will show you how to build a RAG agent using Llama Stack.
Learn more
Stay up-to-date
Our latest updates delivered to your inbox
Subscribe to our newsletter to keep up with the latest Llama updates, releases and more.