Playwright Praman

Playwright Praman is an open-source test harness and agent orchestrator developed by Maheshwar Kanitkar. It is designed to bridge terminal AI coding agents (such as Claude Code and GitHub Copilot CLI agents) with Microsoft Playwright and SAP UI5 / Fiori enterprise web applications. The framework operates by coupling agent definitions—such as dedicated test planners, code generators, and self-healers—with a specialized browser bridge script (`__praman_bridge`). When testing SAP applications, the bridge executes inside the browser session via `@playwright/cli`, tapping directly into SAP UI5's internal `ElementRegistry` and control metadata via `sap.ui.require` to expose semantic control states to the AI agent. Unlike general-purpose browser testing agents that rely solely on raw DOM selectors or standard accessibility trees, Playwright Praman is purpose-built to navigate SAP Fiori elements, List Reports, and Object Pages. It addresses the selector fragility common to dynamically generated UI5 controls by providing runtime inspection and native control resolution. Playwright Praman is an open-source tool hosted on GitHub. It integrates into developer workflows through npm and markdown-based agent definitions tailored for CLI workflows.

Tags: AI, cli, developer tools, OpenSource, productivity

Visit Playwright Praman

Key features

• SAP UI5 Control Discovery — Interrogates live UI5 runtimes and extracts controls using internal ElementRegistry APIs via sap.ui.require. - Specialized Agent Roles — Includes structured agent personas for test planning, Playwright script generation, and session-based test healing. - Browser Bridge Integration — Injects runtime scripts (__praman_bridge) into Playwright CLI sessions to capture UI5 application state. - Fiori Pattern Support — Includes domain scripts for automating common SAP UI patterns, such as List Reports and Object Pages. - Session-Based Test Healing — Reproduces failing test runs in headed or headless sessions, inspecting control states to automatically fix broken assertions and selectors.

Use cases

Use Case: Automated SAP UI5 Test Generation Developers running CLI agents can point the planner and generator agents at an SAP Fiori web page to discover UI5 controls and automatically author structured Playwright test scripts.

Use Case: Self-Healing Flaky Enterprise Tests When UI5 library upgrades or metadata updates break selectors, the healer agent reproduces the session, queries the UI5 ElementRegistry, and rewrites broken locators automatically.

Use Case: CLI-Driven Control Inspection Engineers debugging complex enterprise UI flows can use agent commands to pull runtime control hierarchies, dialog controls, and bridge statuses directly into their terminal context.

Who it is for

Playwright Praman is designed for QA automation engineers and SAP enterprise developers building end-to-end browser tests for UI5 and Fiori applications using CLI coding assistants like Claude Code. It is not intended for teams testing standard semantic HTML web applications that do not utilize the SAP UI5 framework.

Install guide

Installation Install Playwright Praman along with Playwright CLI in your project repository: bash npm install --save-dev playwright-praman @playwright/cli

First Run Configure your Playwright CLI configuration file (e.g., examples/praman-cli.config.json or .playwright/config.json) to register the Praman bridge initialization script: json { "browser": "chromium", "initScript": "../node_modules/playwright-praman/dist/bridge/browser-scripts/bridge-init.js" } Ensure your agent environment (such as Claude Code) has access to the Praman agent definitions located in .claude/agents/.

Example Session Launch a Playwright CLI session connected to your target SAP UI5 application and invoke an agent role: bash npx @playwright/cli open https://your-sap-fiori-app.example.com --config examples/praman-cli.config.json Within your agent CLI prompt, instruct the orchestrator: text Run praman-sap-generator-cli to discover all controls on the active List Report and generate a Playwright test for filtering the table by status.

Part of CLI Coding Agents

Categories: AI Coding Agents, Code Assistants, Developer Tools

Related CLI agents

• PicoClaw — PicoClaw is an open-source command-line coding agent developed by Sipeed and community contributors. Written in Go, it is engineered for…
• GreatCTO — GreatCTO is an open-source AI agent orchestration harness and engineering pipeline framework created by Anatoly Velikiy (avelikiy). It coordinates multi-role…
• Token Optimizer — Token Optimizer is an open-source agent plugin and context optimization harness developed by Alex Greenshpun (alexgreensh). Designed to integrate directly…
• ActPlane — ActPlane is an open-source agent execution and policy enforcement harness developed by the Eunomia-bpf organization. It functions as a security…
• Skillreaper — Skillreaper is an open-source skill lifecycle management and auditing tool for AI agent ecosystems, developed by thousandflowers. It analyzes agent…
• Zosma QA — Zosma QA is an open-source testing-focused agent harness and orchestration framework created by Zosma AI. It provides scaffolding, structured prompt…