Testing

Quality engineering for AI coding agents: a method with steps and human gates, measured by deterministic engines. Runs locally and sends no source code.

CLI and MCP server for Bugpacker bug packages. Give a coding agent the console, network and repro steps from a real bug, without any of it leaving your machine.

Sistema de Inteligência em Qualidade de Software: executa, analisa, prevê, recomenda e aprende. Memória local + Learning Hub.

Unify Claude Code, Codex, Cursor, and Gemini CLI with persistent context, governance, and multi-model debate.

MCP server for Appsurify TestMap — exposes test-coverage analytics (context resolution, ranked coverage gaps, element context, zero-coverage pages) to AI agents.

Pact contract testing for Model Context Protocol (MCP) servers and clients. Ships an ergonomic TypeScript consumer/provider DX and provisions the Rust matching engine (the Pact `mcp` plugin) on install.

CLI and MCP server for termless — terminal capture, screenshots, and AI agent integration

KERNL V2.0 - Persistent Intelligence Layer for AI. Transform Claude from stateless to persistent with 75 tools: crash recovery, semantic search, cross-project learning, system control, and 100% Desktop Commander parity.

Framework-neutral conformance runner, immutable reports, and semantic regression comparison for MCP systems.

Zero-knowledge encrypted secret sharing for AI agents via MCP

X360AIRunTest Web Agent

MCP server for interacting with Android and iOS devices/emulators — screenshots, taps, swipes, typing, UI inspection, and more.

CI for MCP servers: schema contract testing + cross-model regression evals for your agent-facing tools

छोटू — an interactive, role-based AI agent (Dev, QA, and more) that drives MCP servers (browser, Git hosting, Jira, Figma) to do real work. Provider-agnostic: Claude, OpenAI, Gemini, or local models.

Programmatic inboxes that send and receive real email. The agent-facing surface: human and machine readable at once.

Autonomous QA agent - runs browser-based tests via MCP

End-to-end reliability testing for multi-step AI agent workflows. Tests what DeepEval and Langfuse can't: cascading failures across 10+ step chains.

MCP for Roblox Studio and Open Cloud: drive Studio, run headless tests, and review game security.

Cairn — an AI that walks your system and leaves a trail of tests. Autonomous QA agent (UI today; API/unit/docs planned) powered by Claude/OpenRouter, with self-improvement via Langfuse.

ShadowPTY - Headless TUI testing & session recording MCP server