MCP servers and skills: search, filter by where they run, and compare.
Claude Code QA agent with memory, plus a read-only MCP server (verdict-qa-mcp on PyPI): baseline → delta runs (NEW/REGRESSED), a fact harness so the model judges while the system measures, signed run
PythonMIT★ 2Few starsNo key
Open-source test impact analysis for agent-driven CI
PythonApache-2.0★ 2Few starsNo key
MCP server: GitHub Actions CI triage tools for coding agents (read-only)
PythonMITFew starsNo key
Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Markdown). Works with Claude Code, Codex & any MCP host.
PythonAGPL-3.0★ 22No key
AI-powered automated E2E testing. Just enter a URL — AI generates and runs test scenarios.
PythonAGPL-3.0★ 7No key
Background sub-agents for Claude Code, Codex, Kimi and OpenCode over MCP: parallel jobs, one wait, short summaries, engine picked by free quota, monthly API spend cap
PythonMITFew starsNo key
Property-based reliability testing for tool-using AI agents under partial failures.
PythonApache-2.0★ 1Few starsNo key
OpenAPI spec in, chaos test harness out: WireMock stubs, contract tests and failure scenarios from a team of local LLM agents.
PythonMIT★ 2Few starsNo key
Secure Agentic Git Engine: a local-first agentic MCP orchestrator that clones a GitHub repo, reviews and patches it with Groq LLM agents, verifies fixes by running tests, and opens a draft PR.
PythonMIT★ 1Few starsNo key
Probe and test MCP servers with configurable Agent vs Agent conversations
PythonAGPL-3.0★ 1Few starsNo key
MCP server for QA automation: 10 tools, 4 resources, 3 prompts for insurance testing. Full Claude Code ecosystem.
PythonMITFew starsNo key
Who stands behind it
