Appliqation Automation SDK for Playwright — API-key auth, scope-validated result reporting, portable storageState (setupAuth), and customer-defined login flows (defineLogin) for gated apps

Standalone autonomous testing agent that executes Appliqation MCP workflows against a live app under test.

Standalone agent that fixes an Appliqation defect: loads full defect context, locates and applies a code fix, syncs the Appliqation scenario, and verifies the fix by actually running Playwright.

Read-only reporting CLI for the Appliqation agent family's audit trail — how much testing the agentic system did, and how many tokens it used, over a period.

Standalone agent that generates enterprise-grade Playwright automation scripts for Appliqation test cases, grounded in every available signal (manual/agentic execution evidence, defects, flakiness, sibling test cases) and verified by actually running the

Standalone agent that commits local file changes in a repo checkout and opens (or reuses) a pull request. Fully mechanical — no LLM involved — reusable for scripts from appliqation-scriptgen or code changes from any future defect-fix agent.

Interactive installer that scaffolds a local folder of Appliqation standalone agents (autotest, autopilot, scriptgen, defect-fix, heal-selector, visual-regression, explorer, pr-raise, dashboard) with a working .env and ready-to-run CLI/CI commands.

An agentic orchestrator that decides, per test case (or an entire scenario/test set), whether to run autonomous testing, heal a stale selector, fix a defect, generate new automation, or raise a pull request for it — reasoning over real signal (current pas

Standalone agent that heals one broken Playwright selector in an existing script: narrow and token-efficient, never a full regenerate. Verifies a healed selector targets the same semantic element (accessibility role + name, the test case's own expected_re

Standalone agent that runs Appliqation's exploratory-QA workflow (appq:runman) headlessly against a live app under test — the same senior-QA heuristics pass, without a human at the confirmation gate.

Shared engine (think->act->observe loop, budget tracking, appq MCP client, gated tool dispatch, Playwright browser tools, evidence capture) for Appliqation's family of standalone agents.

Standalone agent that checks a page for real visual regressions by diffing it against its own live production counterpart: no stored baseline files, no manual baseline-approval workflow. Declines rather than compares when no production equivalent exists.

Converts Automan-generated Playwright scripts into a Page Object Model structure, without touching the Automan pipeline itself