Install

GenXAI is a Python framework. Install from PyPI:

pip install genxai-framework

See the dedicated Installation page for more options.

Optional extras:

pip install "genxai-framework[llm,tools,api]"

Set your API key

export OPENAI_API_KEY="sk-your-key"

Create a minimal graph workflow

This is a simplified version of the example shown in the repository README.

import os
from genxai import Agent, AgentConfig, AgentRegistry, Graph

os.environ["OPENAI_API_KEY"] = "sk-..."

classifier = Agent(
    id="classifier",
    config=AgentConfig(
        role="Classifier",
        goal="Categorize customer requests",
        llm_model="gpt-4",
    ),
)

support = Agent(
    id="support",
    config=AgentConfig(
        role="Support Agent",
        goal="Resolve customer issues",
        llm_model="claude-3-opus",
        enable_memory=True,
    ),
)

AgentRegistry.register(classifier)
AgentRegistry.register(support)

graph = Graph()
# Add nodes + edges, then run
result = await graph.run(input_data="My app crashed")
print(result)

Next steps

• Read about the system design in Architecture
• Learn coordination patterns in Flows
• Explore runnable samples on the Examples page