96 packages found
MCP server for Human For AI — let your AI agent hire a real human for real-world verification, testing, review, and erra
Pre-execution governance for AI agents. Sub-millisecond tool call validation, drift detection, circuit breakers, human-i
CLI-first API testing tool. YAML-defined tests, structured JSON output, built for AI-assisted workflows.
AI-driven SDLC harness for Claude Code — multi-agent TDD workflow (plan → tests → code → review → PR) with Azure DevOps,
CI for ink stories — compile checks, exhaustive branch playtesting, dead-content detection. MCP server + CLI.
Actor Playwright MCP server
Playwright MCP fork that works with Cloudflare Browser Rendering
A battle-tested skill for managing a professional LinkedIn profile autonomously using Claude AI. 21 automations, 12+ wee
Give AI your browser. Check email, track orders, download receipts -- all authenticated, no API keys. Open source MCP se
Give your AI agent a real browser — with a human in the loop. Open-source MCP-native browser agent.
Claude Code skills for medical research — literature search, reporting guidelines, statistical analysis, publication fig
ABAP Accelerator is an MCP server that helps organizations create, test, document, and transform SAP ABAP code faster an
An Israeli weather MCP server that gives an LLM real browser control via Playwright — it opens a browser, types a city,
Termux Browser Pilot — Firefox/Chromium automation for Android/Termux with CDP, MCP server, and accessibility-first desi
✨✨Latest Advances on Neuro-Symbolic Learning in the era of Large Language Models
Task-induced context normalization for coding agents — a native Claude Code plugin. The task induces a projection; opera
Zero-dependency browser automation CLI. 70+ commands, 10 test assertions, smart commands (click/fill by text — no LLM ne
Self-installing personal AI orchestrator. Hand the latest blueprint file to a Claude Code session and it builds a full m
The open-source web-browsing backend for AI agents & workflow engines. Ships a 42-tool MCP server for Claude Code/Cursor
Claude skill that wraps CloakBrowser stealth Chromium — fetch, screenshot, PDF, and run JS through anti-bot detection (C
Claude 2026: The Developer’s Smartest AI for Long-Context Code & Writing
Autonomous multi-agent SDLC harness: describe a feature in plain English and AI agents scope, code, test, review, and op
A native desktop application for developing, testing, and debugging Model Context Protocol servers.
Google search MCP. One MCP replaces search + fetch + academic-paper extractor.
Autonomous UI debugging MCP server — a fast agent drives the browser/desktop, finds bugs + visual issues, and reports ba
Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGraph, CrewA
Claude Code dynamic workflow for autonomous software engineering. Zero human intervention. Spec-driven, doc-as-ground-
Production-tested CLAUDE.md and rules that make Claude Code write better code and more human text. Anti-AI-slop writing
50 QA and test-automation skills for Claude Code, Codex, Cursor, and any Agent Skills Standard runtime.
Open-source statement-level Playwright tracer, purpose-built for AI agents. Analyzes test runs with increased accuracy.
LinkedIn for AI assistants (MCP) — profiles, people/job/company search, feed & messaging as structured JSON, plus gated
Private browser image workflows for AI agents via MCP
Screen-reader navigation cost analyzer — models the real effort to discover, reach, and operate interactive web content
Depth-first lead finder for a pentest/bug-bounty offering: a FastMCP server (Prospeo contact resolution + lead store) dr
MCP Server for editing VBA code and controls on an MS Access .ACCDB database via LLM (tested just with Claude Code)
LLM 비교 연구 기반 올인원 학습 허브 플랫폼 | GPT-4o · Gemini 2.0 Flash · Claude 4.5 Sonnet 의 정확도 분석을 토대로 학생들이 목적에 맞는 최적 모델을 선택하고 활용할 수 있
Painless E2E Automation for Mobile and Web
达尔文.skill —— 一个让你的Skill无限进化的系统:评估→改进→测试→保留或回滚 | Autoresearch-inspired autonomous skill optimization for Claude Code. Eva
Tired of paying for frontier AI models? Break free with this guide to 100% local, private LLM code generation on Apple S
Agentic QA boilerplate built on Playwright + KATA + TypeScript. Multi-agent skills following the agentskills.io spec, or
AI quantitative trading platform for crypto, stocks, and forex with backtesting, live trading, market data, and multi-ag
A powerful MCP server for Google search that enables parallel searching with multiple keywords simultaneously.
Combining a five-level AI framework with git-native memory overcomes session amnesia, enabling anticipation of problems
Two Claude Code skills for a QA flow: turn a ticket into a reviewed test plan, then execute it in a real browser with Pl
Stealth browser automation that actually works. Runs Camoufox (custom Firefox) in Docker with zero Chrome DevTools Proto
Permanent guardrails for AI-coded apps
MCP server that drives Google Flow (Veo / Nano Banana) through its internal tRPC API, with a hard credit-cost gate
Verifies & compiles reduced-motion-safe, on-budget UI animation for AI-generated web apps. Validated specs → determinist
MCP server for Pipedrive CRM. 155 contract-tested tools, v2-first API, gated destructive ops. Works with Claude Desktop,
CLI, MCP server, and npm library that turns any website into an API — no docs, no SDK, no browser.