feldroy/air

The first web framework designed for AI to write. Built on Python, FastAPI, Pydantic, and HTMX. By the authors of Two Scoops of Django.

What it solves

Air is a web framework designed specifically to be written by AI coding assistants. It removes implicit behaviors and "magic" that often confuse LLMs, providing a fully typed API with comprehensive in-source documentation so that AI agents can understand and use the framework without needing external documentation.

How it works

Built on top of FastAPI, Pydantic, and HTMX, Air allows developers to build web pages using two primary methods:

  • HTML-first: Use Jinja templates to render HTML mockups.
  • Python-first: Use "Air Tags" (typed Python classes) to generate HTML content directly in Python code, enabling autocomplete and type-checking.

It integrates seamlessly with FastAPI, allowing a single project to serve both a REST API and HTML web pages. It also uses Pydantic for HTML form validation.

Who it’s for

Web developers and AI-assisted developers who want to build fast, typed web applications using Python, FastAPI, and HTMX, specifically optimized for AI-driven development workflows.

Highlights

  • AI-Optimized API: Fully typed and documented in-source for better LLM understanding.
  • FastAPI Integration: Leverages FastAPI's routing and capabilities while adding HTML tools.
  • HTMX Friendly: Includes utilities specifically for integrating with HTMX.
  • Dual Rendering: Supports both Jinja templates and Python-based HTML generation (Air Tags).
  • Pydantic Validation: Uses Pydantic for robust HTML form validation.

Related

  • Project
    fastapi/fastapi

    FastAPI is a high‑performance, type‑hint‑driven Python web framework for building APIs. It provides automatic validation, serialization, and interactive OpenAPI docs, while being fast to code and production ready.

  • Project
    neuml/txtai

    An all-in-one AI framework for semantic search, LLM orchestration, and language model workflows, featuring a built-in embeddings database for RAG and autonomous agents.

  • Project
    chenjigang4167/testhub_platform

    TestHub is an open‑source, AI‑enhanced test‑management system built with Django (backend) and Vue 3 (frontend). It covers requirement analysis, test‑case authoring, API/Web/Android automation, performance testing, and reporting, while offering LLM‑driven test generation and a chatbot assistant.

  • Project
    browser-use/browser-use

    A framework that enables AI agents to control a web browser like a human, allowing them to perform tasks such as filling forms and extracting data through plain-language instructions.

  • Project
    i-am-bee/beeai-framework

    A comprehensive toolkit for building production-ready autonomous agents and multi-agent systems in Python and TypeScript, featuring integrated RAG, memory, and multi-LLM support.