Install Vijil Console CLI
Verify the Installation
Initialize the CLI
Point the CLI at your Vijil Console deployment:
Or run vijil init without arguments to be prompted for the URL. The CLI verifies connectivity before saving.
Configuration is stored in ~/.vijil/config.yaml.
Login to Vijil Console
You will be prompted for your email and password. On success the CLI stores your JWT token and automatically selects your team if you belong to exactly one.
If you belong to multiple teams, select one:
The active team ID is injected automatically into commands that require it.
Register an Agent
Create an agent configuration pointing at the AI model you want to evaluate.
To avoid putting secrets directly in your shell history, export your provider API key first:
Required flags:
-
--agent-name — a display name for the agent
-
--model-name — the model identifier (e.g. gpt-4, claude-sonnet-4-20250514)
Optional flags:
-
--agent-url — the endpoint the agent is reachable at
-
--api-key — API key for the agent’s provider
-
--agent-system-prompt — system prompt the agent uses
The output shows the created agent including its id. Copy that ID for the next steps.
List Agents
Output:
Use --json for machine-readable output:
List Available Harnesses
Harnesses are test suites that evaluate different trust dimensions:
Output:
Run an Evaluation
Start a trust evaluation against your agent:
Required flags:
-
--agent-id — UUID of the agent to evaluate
-
--harness-names — JSON array of Harness names to run
Optional flags:
-
--sample-size — number of prompts to run (1-1000); omit to run all
-
--harness-type — standard (default) or custom
-
--wait — poll until the evaluation completes instead of returning immediately
Waiting for Completion
Add --wait to block until the evaluation finishes:
The CLI polls every 5 seconds and prints status updates as the evaluation progresses.
Check Evaluation Status
If you did not use --wait, check the status manually:
Output:
When the evaluation completes, scores appear:
View Evaluation Results
Retrieve the detailed results:
This returns the full results including per-Harness breakdowns and individual Probe results.
Use --json to pipe into other tools:
Generate a Report
Trigger on-demand report generation for the completed evaluation:
To download the generated report as HTML or PDF, use the API directly:
Next Steps
-
Custom Harnesses — create test suites tailored to your use case:
-
Personas — list presets and create personas for testing:
-
Policies — manage compliance policies and rules:
-
Dome Guardrails — configure runtime protection:
-
Red Team Campaigns — run adversarial attack campaigns:
-
Trust Dashboard — view aggregated trust metrics:
Every command supports --help for detailed usage and --json for machine-readable output.Last modified on April 28, 2026
