Test that your Claude Code skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, activation checks, A/B experiments, CI gates.
Like Lighthouse for your agent harness - verify your CLAUDE.md/AGENTS.md, skills & hooks are real, then test and measure they actually work. Claude Code + Codex.
Python foundation for LLM apps whose prompts and spend you can actually see — versioned prompts, every call recorded and replayable, budgets, evals, jobs.
Validate and retry LLM outputs for ruby_llm. Describe the JSON response you expect, fall back to a stronger model when the cheaper one fails the rules, and gate CI on regressions — all as one contract object per step.
Hey LLM, you okay? — pyramid-ordered LLM testing CLI for CI/CD. One YAML for every layer, LLM-as-a-judge gates, and A/B triage that tells prompt regressions from model drift.