autourgos-starter

The fastest way to get a working Autourgos agent running. Bundles the recommended default stack as real pip dependencies (nothing vendored or copied) and gives you one function that wires them together.

from autourgos_starter import create_starter_agent, tool

@tool
def add(a: float, b: float) -> float:
    """Add two numbers together."""
    return a + b

agent = create_starter_agent()
agent.add_tools(add)

result = agent.invoke("What is 12 + 30?")
print(result)

Features

• One function, one working agent — create_starter_agent() wires autourgos-agent + autourgos-openaichat + autourgos-memory together with sensible defaults
• Nothing vendored — every dependency is a real, independently-installable, independently-maintained package
• Optional scaffolding, not a requirement — swap in a different memory or LLM backend any time by using autourgos-agent directly

Table of Contents

• Install
• Quick Start
• What's Actually Happening
• create_starter_agent() Reference
• Also Re-Exported
• License

Install

pip install autourgos-starter

Set your API key:

export OPENAI_API_KEY="sk-..."

Quick Start

This whole block is copy-pasteable — no placeholder variables to fill in.

from autourgos_starter import create_starter_agent, tool

@tool
def add(a: float, b: float) -> float:
    """Add two numbers together."""
    return a + b

agent = create_starter_agent()
agent.add_tools(add)

result = agent.invoke("What is 12 + 30?")
print(result)

That's it — two lines to build the agent (create_starter_agent() and agent.add_tools(add)), one line to run it (agent.invoke(...)).

What's Actually Happening

autourgos-starter is just a convenience wrapper. create_starter_agent() does this:

from autourgos_agent import Agent
from autourgos_openaichat import OpenAIChatModel
from autourgos_memory import RuntimeShortTermMemory

llm = OpenAIChatModel(model="gpt-4o-mini", api_key=None, system_prompt=None)
memory = RuntimeShortTermMemory()  # bounded to 20 messages; pass memory=ConversationBufferMemory() for unbounded
agent = Agent(llm=llm, memory=memory)

Three real, independently-installable packages, each maintained on its own:

• autourgos-agent — the agent loop itself (Agent, tool).
• autourgos-openaichat — the LLM backend (OpenAIChatModel), talks to the OpenAI Chat Completions API or any OpenAI-compatible endpoint (set base_url to point at a local server such as Ollama, LM Studio, or vLLM).
• autourgos-memory — the memory backend (ConversationBufferMemory, RuntimeShortTermMemory, and every other Autourgos memory type).

This package is optional scaffolding, not a requirement to use the Autourgos framework. If you want a different memory backend (e.g. SummaryBufferedMemory, TokenBufferedMemory — both in autourgos-memory) or a different LLM backend (e.g. autourgos-responses), skip autourgos-starter and wire Agent up to those packages directly — that's exactly what this package does under the hood, just with sensible defaults picked for you.

create_starter_agent() Reference

def create_starter_agent(
    api_key: str | None = None,
    model: str = "gpt-4o-mini",
    system_prompt: str | None = None,
    **kwargs,
) -> Agent

Returns an Agent instance. Call agent.add_tools(...) before agent.invoke(...) / agent.ainvoke(...).

Also Re-Exported

So you don't need to know which sub-package a class lives in:

from autourgos_starter import Agent, tool, OpenAIChatModel, ConversationBufferMemory

ReactAgent is also re-exported as a deprecated alias for Agent, for code written against the pre-rename autourgos-react-agent-based version of this package.

License

Apache License 2.0, Copyright (c) 2026 Jitin Kumar Sengar