Skip to main content
This example uses examples/python/agent_deployments/openai_agents_job/nullspace.agent.toml to package an OpenAI Agents SDK app, run it as a finite job, and collect declared outputs.

​
Setup

python -m pip install "nullspace-sdk[cli]==0.1.9"
export NULLSPACE_API_KEY=ns_live_...
export NULLSPACE_API_URL=https://api.your-nullspace-domain
export OPENAI_API_KEY=sk-...
cd examples/python/agent_deployments/openai_agents_job

​
CLI

nullspace agent deploy .

nullspace agent run openai-agents-job \
  --input-json '{"task":"summarize agent deployments"}' \
  --env OPENAI_API_KEY="$OPENAI_API_KEY" \
  --json

nullspace agent logs openai-agents-job --run adrun_123
nullspace agent outputs openai-agents-job --run adrun_123
nullspace agent status openai-agents-job --run adrun_123
nullspace agent delete openai-agents-job --yes
Expected output includes a successful run status and output metadata for result.json plus reports/summary.md.

​
Config

name = "openai-agents-job"
mode = "job"
install = "python -m pip install -e ."
entrypoint = "python main.py"

[env]
required = ["OPENAI_API_KEY"]

[outputs]
paths = ["result.json", "reports"]

​
Python

The companion run.py script uses the same deployment contract through the SDK: 
from pathlib import Path

from nullspace import AgentDeployment

project = Path(__file__).resolve().parent
deployment, version, manifest = AgentDeployment.deploy(path=project)
run = deployment.run(
    input={"task": "Summarize why Agent Deployments are useful."},
    envs={"OPENAI_API_KEY": "..."},
    retain_on_failure=True,
)
outputs = deployment.run_outputs(run.id)
print(deployment.name, version.id, len(manifest.entries), len(outputs.outputs))
Run the complete script: 
python run.py
Related: OpenAI Agents SDK and Agent Deployments.