Launching soon — get early access:
Fume

Fume

AI-Native
Easiest to use
Best output quality
Most customizable

Get an extensive Playwright test suite overnight — autonomous AI QA

SOC 2
EU AI Act: Limited
Global
Public API
No signup
+3
Autonomous
Last updated: Aug 28, 2026
Paid
Visit Site
More
fumedev.com
Fume screenshot 1
Visit fumedev.com

Quick Answer

AI

Fume is an AI agent for software development teams that automates end-to-end browser testing. It generates 100% Playwright code from video recordings, offering self-healing tests and free cloud runners. Best for engineering teams replacing manual QA with an autonomous, code-owning solution. Paid plans start at $500/month with an Enterprise option.

About FumeAI

Fume is an AI agent that transforms Loom-style product videos into comprehensive Playwright end-to-end browser tests. It autonomously designs, writes, and maintains resilient tests, including self-healing capabilities for flaky scripts. Fume offers free cloud test runners and full code ownership, allowing integration into any CI/CD pipeline.

AI-extracted from public sources. May contain errors. Methodology · Report an error
What Makes Fume UniqueAI

Fume uniquely generates 100% Playwright code from video recordings, allowing full code ownership and local execution, unlike no-code builders that lock users into proprietary formats. It also features an AI agent fallback for self-healing flaky tests.

Decision Intelligence

Best For

AI
Growing engineering teams automating browser testing without dedicated QA engineers
Software development teams needing resilient end-to-end tests that self-heal
Organizations migrating existing Playwright, Selenium, or Cypress tests to an AI-powered system
Companies seeking full code ownership and local execution of AI-generated tests
Teams wanting to cover 80% of user flows in under 10 minutes using video descriptions

Consider Alternatives If

AI
Not for non-technical users seeking a no-code test builder
Not for unit or integration testing (focuses on end-to-end browser testing)
Not for teams unwilling to integrate AI into their QA processes
Pricing Overview

Type

Paid

Starting Price

$0/mo

Free Trial

Yes

Credit Card

Not Required

Free Plan

Yes

Dimension Scores

· 6.7 avg

How good it is, across universal quality axes

Ease of Use7/10
Output Quality8/10
Value for Money7/10
Customization5/10
Support7/10
Integration6/10
Accuracy & Reliability8/10
Compliance & Data Protection4/10
Performance5/10
Task Completion8/10
Tool Use Correctness8/10
Planning Quality7/10
AI-analyzed from product data·Medium confidenceHow we score

Task Scores

· 6.7 avg

What it can do, on category-specific tasks

Test Generation9/10
Bug Detection7/10
Refactoring7/10
Context Understanding7/10
Code Explanation6/10
Documentation Generation6/10
Performance Optimization5/10

Scores are AI-estimated from publicly available data — not an independent test or a verified user rating. How we rank →

Capabilities
Automation
Code
Code Review
Categories
Code Assistant
Developer Platform
Automation Agents
ProsAI
  • +Generates 100% Playwright code, ensuring full ownership and local execution
  • +Automates test design, writing, and maintenance, eliminating manual QA work
  • +Self-heals flaky tests using an AI agent fallback, improving test stability
  • +Supports migration of existing Playwright, Selenium, and Cypress tests
  • +Offers free cloud test runners, reducing infrastructure costs
  • +Integrates easily into existing CI/CD pipelines with a single API call
LimitationsAI
  • -Requires video input for test generation, which may not suit all testing methodologies
  • -Focuses primarily on browser testing, potentially limiting scope for other test types
  • -No visual builder or low-code option for non-developers, requiring some technical familiarity
  • -Pricing may be a barrier for very small teams or individual developers
  • -Relies on AI for test generation and maintenance, which may require trust in AI's accuracy
Integrations & Connections
3 connections
PL
PlaywrightNative

Generates and maintains end-to-end browser tests

SE
SeleniumNative

Migrate existing Selenium tests to Fume

CY
CypressNative

Migrate existing Cypress tests to Fume

Auto-updated

Fit Score

Complexity

Advanced

Company Size

Small
Medium
Enterprise

Team Size

Small Team
Large Team

Skill Level

Expert
Features
Video-to-test case extraction
Autonomous test design and writing
Self-healing tests with AI agent fallbacks
Free cloud test runners
100% Playwright code ownership
CI/CD pipeline integration
Migration for existing Playwright, Selenium, and Cypress tests
Explores applications like a human QA engineer
Technical Capabilities
SDK Available
MCP Compatible (unknown)
Multi-Agent
Human-in-Loop (unknown)
Can Use Tools (unknown)
Team Features
Webhook Support
Has Demo
Function Calling (unknown)
Sandbox Mode
Audit Logs
No Signup
Works Offline (unknown)
Requires Host App
Framework
MCP Server
Digital Employee

Deployment

Cloud
Developer Access
Compliance, Privacy & Trust
GDPR (as claimed): No
SOC 2 (as claimed): Yes
Type II
HIPAA (as claimed): No
Trains on user data: Unknown
Human review:
Recommended

Compliance audit trail

1 event
  1. SOC 2

    SOC 2 Type II compliance

    7mo ago · 2026-01-01 · source

Tech Specs
Max upload: 500MB
Response time (est.):
Moderate

The Model(s) Behind It

Model details — extracted from public vendor sources by our pipeline (Smart Generator + A3 cross-referencing) or admin-entered. Shown as claimed by the vendor; not independently audited by Intelloro.

Model Weight Availability
Closed API (no weights)
Training Data Provenance
Not disclosed
Relevant to EU AI Act Art. 53 / Annex XI (GPAI)
Supported Tools
Web Browser
File System
Terminal
Free tier available
Free
Free
    Team Plan
    $500/month
    Free trial · no card needed
    • Autonomous QA
    • 30 day free trial
    Enterprise
    Custom
    • Custom solutions for large organizations
    • Custom pricing and deployment options

    Pricing verified from the vendor pricing page.

    Alternatives

    Top Fume alternatives in the same category, ranked by quality.

    CodeRabbit

    CodeRabbit

    freemium

    AI code reviews — cut review time & bugs in half

    Devika

    Devika

    open_source

    Open-source agentic AI software engineer (open Devin alternative)

    Devin

    Devin

    paid

    The AI software engineer

    Codegen

    Codegen

    freemium

    Enterprise orchestration platform for AI coding agents

    Cline

    Cline

    open_source

    AI coding, open source and uncompromised

    Kiro

    Kiro

    freemium

    Move beyond AI coding to agentic engineering

    Looking for more Fume alternatives?

    Explore our complete list of alternatives with filters for free, cheaper, and higher-rated options.

    View All Alternatives

    User Reviews

    No reviews yet. Be the first to review!

    Who It's For
    4 roles
    Software DevelopersComputer ProgrammersWeb Developers+1 more
    Platform, Content & Languages
    2 content types
    1 languages
    CodeTextEnglish+6 more

    Content Types

    Code
    Text

    Accepts

    Video
    URL
    API

    Produces

    Code
    Text
    API
    Languages: English

    Frequently Asked Questions

    Trust Score

    60/100

    Good

    Based on 6 data signals

    Confidence: Medium

    Reflects publicly available data, not an independent audit

    Compliance & Verified21/38
    SOC 2Yes
    EU AI ActYes
    Human ReviewYes
    Company17/17
    Company ListedYes
    Team Size1-10
    FundingPre-Seed
    Health—

    Not yet checked

    AI-Assisted Data

    Some details are AI-generated estimates — verify with the vendor.

    AI-generated estimate: Best For, Description, Limitations, Not Good For, Pros, Quick Answer, What Makes Unique

    How we source data

    AI Governance & Regulatory Disclosures

    Legally-sensitive fields — extracted from public vendor sources by our pipeline (Smart Generator + A3 cross-referencing) or admin-entered. Shown as claimed by the vendor; not independently audited by Intelloro.

    EU AI Act Risk Tier
    Limited (Article 50 transparency)
    EU AI Act Article 50 Disclosure
    Not declared
    COPPA Compliance (US under-13)
    Not declared

    Switching & Migration

    Migration Difficulty
    Moderate Effort
    Data portable as:
    JS

    Email

    API Access
    Quick Stats
    Agent TypeAutonomous
    PlanningAdvanced
    CategoryCoding Agents
    PlatformsWeb, API
    Launched2024
    Company & Links

    Company Name

    Fume Technologies, Inc.

    Founded

    2024

    Based in

    United States

    Funding

    Pre-Seed

    DocumentationChangelog
    LinkedIn