GeezerVison

Auto-wait and web-first assertions

Playwright waits for elements to be actionable before performing actions. Assertions automatically retry until conditions are met. No artificial timeouts, no flaky tests.

Test isolation

Each test gets a fresh browser context — equivalent to a brand new browser profile. Full isolation with near-zero overhead. Save authentication state once and reuse it across tests.

Resilient locators

Find elements with selectors that mirror how users see the page: getByRole, getByLabel, getByPlaceholder, getByTestId. No brittle CSS paths.

Parallelism and sharding

Tests run in parallel by default across all configured browsers. Shard across multiple machines for faster CI. Full cross-browser coverage on every commit.

Accessibility snapshots, not screenshots

Agents interact with pages through structured accessibility trees — element roles, names, and refs. Deterministic and unambiguous, no vision models required.

MCP server

Drop-in Model Context Protocol server for VS Code, Cursor, Claude Desktop, Windsurf, and any MCP client. Full browser control through standard tool calls.

CLI for coding agents

Token-efficient command-line interface with installable skills. Purpose-built for Claude Code, GitHub Copilot, and similar coding agents that need to balance browser automation with large codebases.

Session monitoring

Visual dashboard with live screencast previews of all running browser sessions. Click any session to zoom in and take control.

Test generator

Record your actions in the browser and Playwright writes the test code. Generate assertions from the recording toolbar. Pick locators by clicking on elements.

Trace Viewer

Full timeline of test execution with DOM snapshots, network requests, console logs, and screenshots at every step. Investigate failures without re-running.

VS Code extension

Run, debug, and generate tests directly in the editor. Set breakpoints, live-inspect locators in the browser, and view full execution traces in the sidebar.