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.
RTL Buddy is a Python CLI for Verilog and SystemVerilog regression testing, Verilator and VCS simulation workflows, coverage, and YAML-based RTL verification automation.
CI for Claude Skills — lint, eval, and regression-test SKILL.md files across a model matrix, with a self-growing eval loop that turns uncovered regressions into permanent test cases.
🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.
Catch broken queries and performance regressions before production. SQL regression testing, EXPLAIN plan baselines, and CI/CD integration for PostgreSQL.
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.
AegisRunner crawls any website from a single URL, discovers every page, form, and interaction, then uses AI to generate a complete Playwright test suite. Also runs accessibility, SEO, security, and performance audits on every page — no recording, no scripting, no setup.