#chaos-engineering

A Kubernetes lab that reproduces real production incidents on a live, instrumented microservice stack — for testing root-cause-analysis tools and agents.

Integrity scenarios for agent runtimes, distilled from real fleet incidents — deterministic fault-injection checks against real SDKs

Do your agent pipeline's own checks catch planted faults? Measured on LangGraph, CrewAI and AutoGen: median 16.7%. One prompt-level change takes it to 55.0%. Pre-registered spec, Apache-2.0 harness, every raw trace published.

Debug, fault-inject and replay AI streaming (SSE) apps. A local proxy, mock LLM and Studio for OpenAI-compatible APIs: inspect every event, inject deterministic failures, record and replay them.