This walkthrough takes you from a Project API key to an agent that has created a file and reported back. You need:

• a Project API key and the API base URL, from your administrator (Issue a Project API key);
• a ready node or E2B backend, so Core has somewhere to run the agent (Nodes);
• Python 3.9 or newer;
• a model: the installation's default model, or your own provider's model ID, base URL and API key. Model execution says which one a Session uses and which protocols each harness speaks.

The example uses Codex, whose model provider must speak the OpenAI Responses API.

1. Connect

Core serves the OpenAI Agents API, so the official OpenAI SDK works unchanged. It reads two environment variables:

Variable	Value
OPENAI_BASE_URL	The API base URL: the public URL plus /v1, such as https://core.example/v1. Web's System page shows it
OPENAI_API_KEY	Your Project API key

python3 -m venv .venv
. .venv/bin/activate
pip install openai==3.13.0
export OPENAI_BASE_URL=https://core.example/v1
read -rs OPENAI_API_KEY && export OPENAI_API_KEY   # paste the key; it is not echoed

Check access. This runs no model and creates no sandbox:

from openai import OpenAI

client = OpenAI()  # reads OPENAI_BASE_URL and OPENAI_API_KEY
print(client.beta.agents.list().data)

An empty list means you are connected. The same check with curl:

curl "$OPENAI_BASE_URL/agents" -H "OpenAI-Beta: agents=v1" \
  -H @<(printf 'Authorization: Bearer %s\n' "$OPENAI_API_KEY")

2. Start a Session

A Session is one agent conversation with its own workspace. With openai_hosted, Core creates a sandbox for it on a node or E2B and starts the harness inside.

With the installation's default model, skip this. To use your own provider:

export MODEL_NAME='your-model-id'
export MODEL_BASE_URL='https://your-provider.example/v1'
read -rs MODEL_API_KEY && export MODEL_API_KEY

import os

extra = {"agent": {"x_agents_core": {"harness": "codex"}}}
if os.environ.get("MODEL_API_KEY"):
    extra["agent"]["model"] = os.environ["MODEL_NAME"]
    extra["x_agents_core"] = {"model_provider": {
        "protocol": "responses",
        "base_url": os.environ["MODEL_BASE_URL"],
        "api_key": os.environ["MODEL_API_KEY"],
    }}

session = client.beta.agents.sessions.create(
    environment={"type": "openai_hosted"},
    input="Create /workspace/hello.txt with a short greeting, then describe it.",
    extra_body=extra,
)
print(session.id)

This makes a real model request and may incur charges.

• x_agents_core holds Core's additions to the OpenAI API; see Core extensions.
• Keep the whole agent object in extra_body. SDK 3.13.0 replaces a body field with the matching extra_body field instead of merging them.

3. Wait for the result

A Session ID confirms creation, not success. Poll durable state; never resubmit to "retry":

import time

for _ in range(120):
    turns = client.beta.agents.sessions.turns.list(session.id, order="desc").data
    if turns and turns[0].status in {"completed", "failed", "cancelled"}:
        turn = turns[0]
        print("Turn:", turn.id, turn.status)
        print(client.beta.agents.sessions.items.list(session.id).data)
        break
    if client.beta.agents.sessions.retrieve(session.id).status == "failed":
        raise RuntimeError("Session preparation failed; inspect its Environment")
    time.sleep(1)
else:
    raise TimeoutError(f"Session {session.id} is still running; inspect it before retrying")

Success is a completed Turn whose Items describe the new file. A timeout neither cancels the work nor proves it failed.

Next steps

To	Read
Stream output, send follow-up messages, upload files, add Skills or MCP, cancel	Agents API guide
See every resource with request and response examples	Agents API guide
Run the agent on your own machine	Self-hosted execution
See a complete application	Examples