How Valkyrie works

Valkyrie orchestrates agentic benchmark runs across sandboxed tasks. Use the CLI or Python SDK to start runs, monitor progress, and retrieve results.

Run your first benchmark

Install the CLI, configure credentials, and start a run.

Upload, list, download, and remove agent bundles.

Connect Valkyrie to a custom benchmark endpoint.

Review the AWS architecture and deployment requirements.

Agent: a bundled program with a contract that tells Valkyrie how to install and run it.
Benchmark service: an HTTP service that provides tasks and evaluates results.
Run: one execution of an agent against a benchmark dataset.
Sandbox provider: the service that creates isolated task environments.

Use the CLI for interactive setup, agent packaging, and run operations. Use the Python SDK to integrate run management into an application.