Juspay Agentic Framework (JAF-PY)¶
A production-ready, purely functional framework for building robust and type-safe AI agents in Python.
Overview¶
JAF follows functional programming principles for predictable, testable AI systems:
- Immutable State: All core data structures are deeply immutable
- Pure Functions: Core logic is side-effect free and predictable
- Type Safety: Leverages Python's type system with Pydantic
- Effects at Edge: Side effects isolated in Provider modules
Quick Example¶
from jaf import Agent, function_tool
@function_tool
async def calculate(expression: str, context) -> str:
"""Perform safe arithmetic calculations.
Args:
expression: Math expression to evaluate (e.g., '2 + 3', '10 * 5')
"""
allowed_chars = set('0123456789+-*/(). ')
if not all(c in allowed_chars for c in expression):
return 'Error: Invalid characters'
try:
result = eval(expression)
return f'{expression} = {result}'
except Exception:
return 'Error: Invalid expression'
agent = Agent(
name='MathAgent',
instructions=lambda state: 'You are a helpful math assistant.',
tools=[calculate]
)
Installation¶
Documentation¶
- Getting Started - Build your first agent
- Core Concepts - Understand the architecture
- API Reference - Complete documentation
- Examples - Working code samples