Flama for your AI assistant
Download the skill.md file and let your AI coding assistant build Flama apps with full framework knowledge.
Core
The building blocks every Flama application shares, whatever you are serving.
Quickstart
Follow this guide to develop your first API, and explore the main functionality offered by Flama. Learn how to create a new project, define your first endpoint, and run your API locally.
Fundamentals
Deep dive into the foundational building blocks of Flama. Learn how applications, routes, schemas, components, modules, middlewares, endpoints, and resources work together to form a coherent ASGI application.
CLI
Discover the Flama command line interface, and uncover the power of codeless model serving. This guide shows how to run an API locally, serve predictive and generative models, fetch and upgrade, and interact with them, without typing a single line of code.
Advanced
Explore advanced features such as configuration management, pagination, error handling, background tasks, lifespan events, authentication with JWT, and other production-ready patterns for building robust APIs.
Flavours
Specialised tracks for the kind of system you are building.
Predictive AI
Learn how to package your ML models as lightweight binary files, integrate them into your API, and customise the interaction with models through Components and Resources for full control over their lifecycle.
Generative AI
Learn how to serve large language models with a first-class serving layer, and expose them through OpenAI, Anthropic, and Ollama compatible endpoints. Integrate a built-in chatbot, and provide tools to AI agents through the Model Context Protocol.
Domain Driven Design
Place your business domain at the centre of your architecture. Learn how to apply Domain-Driven Design patterns within Flama, including repositories, workers, and domain models, to build maintainable systems.
Contribute to Flama
Found a bug, missing a feature, or want to improve the docs? Learn how to get involved and help shape the future of Flama.