Compute
Local and Dreadnode-hosted compute modes for AI red teaming operations.
AI red teaming attacks can execute in two modes: locally on your machine or in Dreadnode-hosted sandboxes. Both modes send results to the platform for analytics and reporting.
Local mode
Section titled “Local mode”When you launch the TUI or run CLI commands locally, all attack execution happens on your machine:
dn --capability ai-red-teaming --model openai/gpt-4oIn local mode:
- Attacks execute on your local machine using your local Python environment
- You provide API keys for the target, attacker, and judge models via environment variables (see Prerequisites)
- Results, traces, and findings are uploaded to the Dreadnode platform automatically
- You can see the attack overview, findings, analytics, and compliance mapping in the platform dashboard
- You only pay for storage of the data in the platform and inference costs if you use Dreadnode-hosted models (dn prefix). There is no compute charge for local execution.
This is the simplest way to get started. No sandbox provisioning, no runtime configuration. Just set your API keys and run.
Dreadnode-hosted compute
Section titled “Dreadnode-hosted compute”When you attach to a Dreadnode runtime, attacks execute inside isolated Dreadnode sandboxes:
dn --capability ai-red-teaming --model openai/gpt-4o --runtime-server <runtime-url>In Dreadnode-hosted mode:
- Attacks execute in isolated sandbox containers managed by Dreadnode
- API keys are configured as Secrets in the platform and injected into sandboxes automatically
- Model calls route through the platform’s model proxy with usage tracking
- Sandboxes are provisioned automatically when you start an assessment
- Dreadnode charges for sandbox compute time in addition to model inference and storage
- Usage is visible in Credits
Use Dreadnode-hosted compute when you need:
- Isolation from your local environment
- Centrally managed secrets and API keys
- Consistent execution environment across team members
- Long-running campaigns that should not depend on your local machine staying online
Inspect a sandbox
Section titled “Inspect a sandbox”dn airt sandbox <assessment-id>Comparison
Section titled “Comparison”| Local mode | Dreadnode-hosted | |
|---|---|---|
| Launch | dn --capability ai-red-teaming --model openai/gpt-4o | dn --capability ai-red-teaming --model openai/gpt-4o --runtime-server <url> |
| API keys | Environment variables on your machine | Platform Secrets |
| Execution | Your local machine | Dreadnode sandboxes |
| Status bar | Shows local | Shows remote |
| Platform results | Yes, uploaded automatically | Yes, streamed in real time |
| Cost | Storage + inference (if using dn models) | Storage + inference + sandbox compute |
| Best for | Getting started, development, quick tests | Production operations, team use, long campaigns |
Next steps
Section titled “Next steps”- Prerequisites - set up authentication, API keys, and compute mode
- Using the TUI Agent - launch AI red teaming
- Using the SDK - programmatic attack workflows