agentry

dortort/agentry

★ 0 stars TypeScript AI/LLM Updated today

Playwright for AI Agents — end-to-end testing for agent CLIs, MCP servers, and skills. Drive a real agent, assert on what it did, replay deterministically in CI.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "agentry": {
      "command": "npx",
      "args": [
        "-y",
        "dortort/agentry"
      ]
    }
  }
}

README Excerpt

<h1 align="center"> <img src="assets/hero.png" alt="Agentry — Playwright for AI Agents" width="100%"> </h1> > **Playwright for AI Agents** — end-to-end testing for the infrastructure AI agents interact with. **Status:** Early MVP — Claude driver, structural assertions, record/replay. No published npm package yet. See [Roadmap](#roadmap).

Tools (11)

agentagentrydryexpectlivemcpread_filerecordtoHaveReceivedtoMatchSchemaworkspace

Topics

agent-testingai-agentsclaudeclaude-codee2e-testingllmmcptest-frameworktestingtypescript

agentry

Quick Install

README Excerpt

Tools (11)

Topics

Related AI/LLM Servers