248 packages found
Agentic QA boilerplate built on Playwright + KATA + TypeScript. Multi-agent skills following the agentskills.io spec, or
CLI-first API testing tool. YAML-defined tests, structured JSON output, built for AI-assisted workflows.
AI 測試大師 — MCP server driving pytest / Jest / Cypress / Go / Maestro. Analyze, generate, run, advise. Web + Mobile (iOS/A
A MCP server that bridges TestDino with AI agents such as Cursor and Claude. Navigate test results, analyze failures, an
Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGraph, CrewA
Self-installing personal AI orchestrator. Hand the latest blueprint file to a Claude Code session and it builds a full m
🧠 Kotlin MCP Server for Android app development using OpenAI, Gemini, or OpenRouter. Enables AI-assisted coding via Aid
Model Context Protocol (MCP) server for Go using gopls – LSP-powered analysis, tests, coverage, and tooling.
AI-powered QA pipeline: Playwright tests + Claude API agent that classifies failures, auto-heals broken locators via PR,
MCP Server for editing VBA code and controls on an MS Access .ACCDB database via LLM (tested just with Claude Code)
AI-driven SDLC harness for Claude Code — multi-agent TDD workflow (plan → tests → code → review → PR) with Azure DevOps,
Screen-reader navigation cost analyzer — models the real effort to discover, reach, and operate interactive web content
AI coding workstation: Claude Code + web UI + 7 AI CLIs + headless browser + 50+ tools
End-to-end and API automation for OrangeHRM and the Restful Booker API — built as a reference implementation showcasing
@microsoft✓ OfficialWindows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.
A native desktop application for developing, testing, and debugging Model Context Protocol servers.
@modelcontextprotocol✓ OfficialConformance Tests for MCP
Turn ad-hoc Claude Code / Codex / Cursor sessions into a repeatable loop — research → plan → wave-execute → close. Paral
This server enables AI assistants to run Xcode tests, perform linter analysis, and provide detailed feedback on iOS proj
VSCode Extension for the Browser DevTools MCP Server which is a Playwright-based MCP server that exposes a live browser
Claude Code plugin that stops "almost done" loops — declare your stages in workflow.json, runs them as a state machine t
Build Claude Code–style deep agents in Python: tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints
Plugin for JADX to integrate MCP server
Media Gen MCP — Strict TypeScript MCP server for OpenAI gpt-image-1 and sora-2: generate, edit, and fetch images/video w
4-stage evaluation framework for testing Claude Code plugin component triggering. Validates skills, agents, and commands
AI coding workstation: OpenCode + Claude subscription support + 30+ tools + headless browser + multi-agent orchestration
🪈 Intelligent orchestration system that coordinates multiple AI coding assistants (Claude, Codex, Gemini CLI, Copilot C
Currents MCP Server
AI-Hedge-Fund for Crypto 🚀 AI-powered hedge fund for cryptocurrency trading, leveraging LLM agents for intelligent dec
Backtrader-powered backtesting framework for algorithmic trading, featuring 20+ strategies, multi-market support, CLI to
Reproducible evaluation for AI coding agents. Multi-turn scenarios against Claude Code, Codex, Copilot, Cursor, Gemini C
acrawl — LLM-powered web crawler. Describe what you want in plain English, get structured data back. Single Rust binary,
Zero-dependency browser automation CLI. 70+ commands, 10 test assertions, smart commands (click/fill by text — no LLM ne
📄 Production-ready MCP server for PDF processing - 5-10x faster with parallel processing and 94%+ test coverage
Combining a five-level AI framework with git-native memory overcomes session amnesia, enabling anticipation of problems
Offline MCP server: an AI agent transpiles PineScript v6 → C++ and runs deterministic, TradingView-parity backtests loca
MCP server for LinkedIn publishing, commenting, and reacting. Dry-run by default, SKILL.md included, 28 unit tests. MIT
ConcoLLMic: the first language- and theory-agonistic concolic execution engine via LLM agents
DevoxxGenie is a plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud
A Model Context Protocol (MCP) integration that provides Claude Desktop with autonomous browser automation capabilities.
MCP (Model Context Protocol) server for Chrome automation using Puppeteer. Persistent browser sessions, visual testing,
A MCP (Model Context Protocol) client that uses Google Gemini AI models for intelligent tool usage and conversation hand
MCP server for computer use & browser automation - screenshot, OCR, click, type, find_text, Chrome/Electron CDP, templa
MCP server for App Store Connect API - 389 tools for apps, builds, TestFlight, subscriptions, Xcode Cloud, and more from
The merge gate for AI-written code, with signed, replayable attestation. Works across Claude Code, Codex, Cursor, and Ge
MCP server for on-premises Azure DevOps Server (TFS) with TFVC support - shelvesets, changesets, Work Items, Git, Pipeli
Benchmarking the gap between AI agent hype and architecture. Three agent archetypes, 73-point performance spread, stress
MCP Testing Tool — Like Postman, but for the Model Context Protocol.
Local-first browser automation MCP for Claude Code / Cursor. taprun compiles once with AI, your authenticated Chrome rep