Fume (YC W24)

Fume is an AI testing tool that automates end-to-end browser testing. It creates and maintains Playwright tests from Loom-style videos, acting as an autonomous QA team.

Claim this tool

1View

At a glance

Pricing

Paid · Enterprise

Free tier

API

Yes

Skill level

Technical

About

What is Fume (YC W24)?

Fume is an AI testing tool designed to automate end-to-end browser testing by acting as an autonomous QA team. Users record a Loom-style video describing what they want to test, and Fume generates and maintains Playwright tests. It extracts test cases in seconds, covering major user flows quickly. Fume offers self-healing tests with AI agent fallbacks for Playwright's fragility, ensuring tests continue even if scripts break. It provides free test runners in the cloud and allows full ownership of the generated Playwright code, which can be run locally or integrated into existing CI/CD pipelines. Fume also supports migrating existing Playwright, Selenium, or Cypress tests.

Best used for

Ideal for developers and QA engineers who need to rapidly create, maintain, and run end-to-end browser tests. Especially valuable for teams looking to automate their QA process, ensure test resilience against UI changes, and integrate testing seamlessly into their CI/CD pipelines.

Common actions

automate testing

generate tests

maintain tests

run browser tests

migrate tests

code assistant

Capabilities

Key features

Video-to-test case generation
Playwright test creation
AI agent fallbacks
Self-healing tests
Free cloud test runners
Full Playwright code ownership
Existing test migration

Target Audience

developerQA engineer

Integrations

github-actionsgitlab

Pricing & Plans

Paid · Enterprise

Contact for Pricing

FAQs

How does Fume generate tests from a video?

Fume analyzes a screencast video where you describe the desired test flow and application behavior. It then extracts test cases and generates corresponding Playwright end-to-end browser tests based on your narration and navigation.

Do I own the Playwright code generated by Fume?

Yes, Fume ensures 100% ownership of the generated Playwright code. You can run these tests locally, integrate them into your CI/CD, and retain full control even if you cancel your subscription.

How does Fume handle broken tests or UI changes?

Fume employs AI agent fallbacks to self-heal tests. If a Playwright script breaks due to UI changes, the AI agent picks up where it left off, and Fume updates the test code in the background to maintain stability.

Can I migrate my existing tests to Fume?

Yes, Fume supports migrating existing Playwright, Selenium, or Cypress tests. It can convert these tests and then apply its native AI fallbacks and auto-maintenance features to them.

Trending

Subcategories trending in Coding & Development

Open Source & Models Code Assistants DevOps & Infrastructure No-Code / Low-Code Backend & APIs Prompt Engineering

Trending

Also listed in

This tool also appears in

AI Agents & Automation › RPA AI Agents & Automation › Workflow Agents

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce