Behavior contracts for AI agents
Playwright for AI Agents. Test what your agent DOES, not what it SAYS. YAML-first behavioral testing. Catch PII leaks, tool abuse, step explosions. 3200+ tests.
Fixture-based approval testing CLI for agent-managed codebases
Catch runtime behavior changes in dependency-upgrade pull requests, even when tests stay green.
Behavior test framework for AI agents. Define tests in YAML. Run against transcripts. Get scored reports.
Upgrade the model. Keep the agent's promises — deterministic compatibility gates for recorded observable AI-agent behavior, with CLI, SDK, CI, reports, and MCP.
Add a description, image, and links to the behavior-testing topic page so that developers can more easily learn about it.
To associate your repository with the behavior-testing topic, visit your repo's landing page and select "manage topics."