Enables stock assessment and replenishment by exposing three deterministic tools: inspect stock positions, raise replenishment orders, and check order status. Includes an auditable local client and follows a security-first design with limited API surface.
Enables benchmarking of Large Language Model APIs by measuring performance metrics such as generation throughput, prompt throughput, and Time To First Token (TTFT) with configurable concurrency levels and parameters.
Turns natural-language API descriptions into runnable k6 load tests, executes them, and returns structured performance metrics for AI-assisted reporting.
Enables AI assistants to investigate and safely resolve commerce order exceptions, such as expired inventory reservations, by providing a workflow across synthetic order, payment, inventory, and fulfillment systems.
Enables testing AI safety classifier robustness against query decomposition, obfuscation, and multi-agent attacks. Provides tools for full evaluation pipelines, query previews, and status checks.
Turn any OpenAPI 3.x spec into a runnable, stateful API environment for AI agents.
Test real integration flows — multi-step workflows, persistent state, webhook delivery, retries, and edge cases — instead of guessing from docs or mocking endpoints.
Generate committable markdown reports directly from Claude/Cursor. Includes 50+ pre-validated APIs like Stripe, GitHub, Twilio, OpenAI, and more.
