Last updated 06-29-2026
Category:
Reviews:
Join thousands of AI enthusiasts in the World of AI!
Debugg AI
Debugg AI runs automated browser tests on your pull requests and posts pass/fail results directly in GitHub comments. Connect a repo through the GitHub App, and the platform handles cloning, building, secure tunneling, and real browser sessions without local Playwright or Selenium setup.
The service maps your application with an agent that explores pages, interactions, and user flows before running targeted end-to-end checks. That knowledge graph helps tests focus on the flows that matter for each change instead of running a fixed script every time.
It fits solo developers, open source maintainers, and QA-minded teams who want UI regressions caught before merge. You can also test a local dev server on demand through managed remote browsers, or wire the DebuggAI MCP server into Claude, Cursor, or other MCP clients so coding agents verify work in a real browser before opening a PR.
GitHub App installs in minutes and posts E2E results as inline PR comments with recordings
Managed browsers run tests without local Playwright drivers or container setup on your machine
AI explores your app to map pages and flows before choosing what to test on each PR
Spin up remote browsers against localhost through an auto-created secure tunnel
MCP server exposes 21 tools so Claude, Cursor, and other agents can check apps in real browsers
Text-based test suites let you describe checks in plain language instead of writing scripts
On-demand runs replay failures step by step with full session recordings
Posts browser test results directly in GitHub pull request comments with video recordings.
No local browser automation setup required thanks to managed remote browsers.
Free tier covers public repositories with a meaningful monthly test allowance.
MCP server lets coding agents verify UI flows against localhost or staging URLs.
Private repositories and higher test volumes require a paid plan starting at $20 per month.
Primary workflow is GitHub-centric, so teams on other Git hosts need to evaluate fit.
Enterprise features such as SSO/SAML require contacting sales on a custom plan.
Is Debugg AI free to use?
Yes. Debugg AI offers a free tier for public repositories with 100 tests per month, PR comments, and community support. Paid Pro and Grow plans add private repos, higher test limits, and priority support.
How does Debugg AI know what to test in a pull request?
Debugg AI analyzes your codebase and uses an application knowledge graph built from exploring pages and user flows. That context helps the platform run targeted browser tests relevant to the changes in each PR.
Do I need to configure Playwright or Selenium locally?
No. Debugg AI provides fully managed remote browsers and handles repository cloning, builds, tunneling, and test execution. The marketing site describes setup as taking about two minutes through the GitHub App.
Can Debugg AI test my local development server?
Yes. You can point tests at a local URL such as localhost, and Debugg AI creates a secure tunnel so managed remote browsers reach your running app without manual ngrok configuration.
Does Debugg AI work with MCP clients like Claude and Cursor?
Yes. The DebuggAI MCP server supports Claude Desktop, Claude Code, Cursor, and other MCP clients. Install with npx @debugg-ai/debugg-ai-mcp and an API key from app.debugg.ai.