Agent Deployment Job

This example uses examples/python/agent_deployments/minimal_job/nullspace.agent.toml to package a small Python project, run it as a job, and collect declared outputs.

Setup

uv pip install "nullspace-sdk[cli]==1.0.0"
export NULLSPACE_API_KEY=ns_live_...
export NULLSPACE_API_URL=https://api.your-nullspace-domain
cd examples/python/agent_deployments/minimal_job

CLI

nullspace agent deploy .

nullspace agent run minimal-job-agent \
  --input-json '{"subject":"agent deployments"}' \
  --env EXAMPLE_AGENT_GREETING=hello \
  --json

nullspace agent logs minimal-job-agent --run adrun_123
nullspace agent outputs minimal-job-agent --run adrun_123
nullspace agent status minimal-job-agent --run adrun_123
nullspace agent delete minimal-job-agent --yes

Expected output includes a successful run status, a stdout line beginning with minimal job wrote result.json, and output metadata for result.json plus reports/summary.txt.

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={"subject": "agent deployments"},
    envs={"EXAMPLE_AGENT_GREETING": "hello"},
    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

Project Files

examples/python/agent_deployments/minimal_job/
  README.md
  main.py
  run.py
  nullspace.agent.toml

Related: Agent Deployments and CLI reference.

Overview

Machine patterns

Networking and access

Agent deployments

Agent Deployment Job

Setup

CLI

Python

Project Files

​Setup

​CLI

​Python

​Project Files

Setup

CLI

Python

Project Files