Skip to main content

​
What is A1?

A1 is a direct replacement for agent frameworks. While prior art generates a static while loop program for each agent, an agent compiler generates a program optimized for each unique agent input.

​
Why use an agent compiler?

  1. Safety - Minimizes exposure of sensitive data to an LLM.
  2. Speed - Up to 10x faster code generation.
  3. Determinism - Code is optimized for minimal non-deterministic behavior (e.g. LLM calls replaced with code where possible).
  4. Flexibility - Skills and Tools from any existing OpenAPI, MCP server, databases, fsspec paths, Python functions

​
Key Features

Agents

Specify what is expected of an agent

Tools

Create tools from existing APIs and databases

Skills

Create skills to codify how to do things

Compilation

Run your agent

​
Quick Example

pip install a1-compiler

from a1 import Agent, tool, LLM
from pydantic import BaseModel

@tool
async def add(a: int, b: int) -> int:
    return a + b

class MathInput(BaseModel):
    problem: str

class MathOutput(BaseModel):
    answer: int

agent = Agent(
    name="math_agent",
    description="Solves simple math problems",
    input_schema=MathInput,
    output_schema=MathOutput,
    tools=[add, LLM("gpt-4.1")],
)

# Compile ahead-of-time
compiled = await agent.aot()
result = await compiled.execute(problem="What is 2 + 2?")

# Or execute just-in-time
result = await agent.jit(problem="What is 5 + 3?")

​
Get Started

Installation

Set up A1 in your environment

Quick Start

Build your first agent

Compilation Guide

Learn about AOT vs JIT

API Reference

Explore the full API