AI-native web testing: describe what to test in plain English, and Argus plans, executes, and reports — no scripts required.

An open-source, multi-agent AI framework for Playwright test automation — featuring a 2D pixel-art office, live SSE telemetry, and Gemini / Ollama LLM routing.

Open-core AI bug reporting & testing — right-click to file grounded bugs to Jira/Linear/GitHub/Plane, AI personas (Sims) that review your product, and self-healing end-to-end tests.

🔍 AI-powered autonomous UI testing — describe what to test in plain English, a pipeline of specialized agents will navigate, write, execute, and self-heal the test automatically.

Your tests have nine lives — self-healing QA for the coding-agent era

AI-powered mobile testing framework with self-healing tests and automatic test generation from user behavior

AI-powered web automation testing workbench with Playwright, natural-language test authoring, and auditable self-healing selectors.

Self-healing locators leverage AI to automatically detect and repair broken element locators in automated tests, ensuring test stability even when the underlying UI structure or attributes change.

AI agent that explores any web app, generates Playwright tests, executes them, and self-heals broken selectors — powered by Claude API

A smart locator library for Playwright with intelligent element detection and robust locator strategies

AI Test Agent — Electron desktop app using Claude AI to auto-generate test cases, Cypress/Playwright frameworks, and self-healing automation scripts from requirements documents.

AI skill for Playwright frontend E2E testing: natural language → spec/flow, self-healing failure recovery, VRT, dynamic-shard CI.

A multi-agent OSINT (Open Source Intelligence) tool built with LangGraph for exploring digital footprints. Leverages parallel execution to search platforms (Google, LinkedIn, X, GitHub, etc.), correlates behavioral patterns, and generates comprehensive intelligence reports. Includes an AI-powered self-healing UI test suite.

AI-powered test automation framework: plain-English user story → executable, self-healing test suite (Claude AI + Playwright + RestAssured + Allure)

Production-grade multi-agent QA pipeline built with LangGraph that autonomously generates, executes, self-heals, and evaluates API test suites from PR diffs and OpenAPI specs. Features LLM-as-Judge coverage scoring, ChromaDB test memory, 5-type self-healing, and human-in-the-loop checkpoints.

AI-powered self-healing browser automation platform

AI Systems Engineering Workbench for Test Automation — structured generation, explainable healing, evaluation, observability, and benchmark-driven improvement of Playwright test suites.

Self-healing browser tests on E2B sandboxes with Vercel AI SDK and multi-model fallback (Claude / GPT / Gemini). Apache-2.0.

Record once. Get a stable, production-ready Playwright test automatically. A no-code QA solution powered by Claude Code skills.

AI-powered self-healing Selenium framework that autonomously detects broken test selectors, generates ranked repairs via Claude Sonnet + LangGraph, validates fixes through multi-layer protocols, and routes results by confidence — auto-commit, PR, or issue escalation. Zero human intervention needed.