AI vision test generation
Describe a user flow in plain English and let the vision agent click, type, and read the screen before writing the test. The homepage says this avoids selectors, DOM access, and setup work.
TestDriver
Freemium
TestDriver est une plateforme de test basée sur l’IA qui automatise les tests de bout en bout sur le web, desktop et les extensions, avec CI, replays et journaux d’échec.
Qu'est-ce que TestDriver ?
TestDriver is an AI-powered testing platform for automating desktop and application workflows with pixel-based vision rather than selectors or DOM access. The homepage positions it as a way to make end-to-end testing faster, more reliable, and easier to maintain.
It is aimed at teams that need to test web apps, browser extensions, editor extensions, and desktop applications on real Windows, macOS, and Linux environments. The product combines AI-driven test creation, cached element matching, visual assertions, and CI-friendly execution in a single workflow.
The pricing page shows a free Cloud plan, paid Cloud plans, and an enterprise self-hosted option, with higher tiers adding more parallel tests, more included minutes, recordings, analytics, private support, and on the enterprise tier, custom implementation and environment control.
In practice, TestDriver is built for teams that want to describe flows in natural language, run them as JavaScript tests, and inspect run artifacts when something breaks. The site also highlights support for third-party web apps and rich UI content such as file uploads, PDFs, and embedded media.
Que peut faire TestDriver ?
Element caching for repeat runs
Tests are cached by element fingerprint so repeated runs can replay quickly and deterministically when the UI has not changed. The site says this reduces token use and keeps passing tests fast.
Self-healing element matching
When an element changes location or appearance, TestDriver re-runs the AI to find it and updates the cache instead of forcing a rewrite. This is presented as a way to keep tests passing through UI changes.
Vitest-based execution in CI
TestDriver describes its tests as plain Vitest that run on real VMs across web, desktop, and extensions. That lets teams use a familiar test format inside their existing CI pipeline.
AI assertions with cached results
The product can validate outcomes with AI-backed assertions and return a boolean result with reasoning. The homepage notes that assertions are cached as well.
Run history and debug artifacts
Debugging output includes video replay, network logs, request details, CPU and memory data, and a step-by-step action log. These views are meant to make failing runs easier to inspect.
Cas d'utilisation
“Create end-to-end tests from natural language”
Use TestDriver to describe a business flow in plain English and turn it into a runnable test that clicks, types, and validates the screen state without relying on selectors.
“Automate regression checks in CI”
Run the same test format in CI so teams can verify app behavior on every commit or pull request and compare local and pipeline results.
“Cover apps beyond standard web pages”
Test browser extensions, editor extensions, and native desktop apps in their real environments, including interfaces that are difficult for selector-based tools to cover.
“Debug failing runs”
Inspect video replays, request logs, action history, and CPU or memory data to understand why a run failed and where the interaction diverged.
“Maintain tests through UI changes”
Use the cached element model and AI re-matching to keep tests stable when layouts shift, text moves, or UI components are redesigned.
Questions fréquentes
How does TestDriver fit into a testing workflow?
TestDriver is designed to write tests from plain-English flow descriptions with its AI vision agent, then run those tests through a familiar JavaScript API. The homepage also shows an example setup command, `npx testdriverai init`, and the pricing page indicates a free Cloud tier and paid plans for more usage and platforms.
What platforms does TestDriver support?
The homepage says TestDriver supports web apps, Chrome extensions, VS Code extensions, Windows apps, macOS apps, and Linux apps. The pricing page also lists mobile targets, but the enterprise self-hosted plan marks Android and iOS as coming soon.
What pricing options are available?
The pricing page shows a free Cloud plan, a Pro Cloud plan, a Team Cloud plan, and an Enterprise self-hosted option with contact sales pricing. The page also notes different included minutes, parallel test limits, and support levels by plan.
What does TestDriver provide when a test fails?
TestDriver records test runs and can surface video replays, network logs, request details, CPU and memory data, and an action log. The homepage presents these as debugging and validation tools for understanding failures and assertions.
Is there enough information here to describe setup in detail?
The source does not document a full onboarding guide, but it shows the product can be initialized with `npx testdriverai init` and then used with AI vision-based test generation and Vitest-style tests.
Informations rapides
- Category
- AI testing platform
- Primary use
- End-to-end testing with AI vision
- Platforms
- Web, Chrome extensions, VS Code extensions, Windows, macOS, Linux
- Hosting
- Cloud and self-hosted
- Pricing model
- Free tier, paid Cloud plans, and enterprise contact sales
- Source domain
- testdriver.ai
Analyse du trafic de TestDriver
Les données de trafic sont fournies à titre indicatif uniquement.
- Évaluation du domaine
- 57
Alternatives à TestDriver
Penligent
penligent.ai
Penligent est une plateforme de tests d’intrusion assistés par l’AI pour les équipes de sécurité, les pentesters et les red teams. Elle automatise la découverte, la validation, la reproduction d’exploits et les rapports fondés sur des preuves pour les applications web, les API, la logique métier et les agents AI.
OpenHands
openhands.dev
OpenHands est une plateforme open source et agnostique des modèles pour agents de programmation cloud, qui automatise les workflows d’ingénierie via le Web, la CLI, l’interface terminal et le SDK, avec des déploiements locaux, cloud et d’entreprise.
Equixly
equixly.com
Equixly est une plateforme de sécurité offensive pour tester en continu les API et applications avec un Agentic AI Hacker.
Scorecard
scorecard.io
Scorecard est une plateforme de test et d’évaluation de l’IA pour les équipes qui créent des agents et produits LLM.
Hoplite
hoplite.sh
Hoplite est une plateforme d’agents de programmation qui exécutent des tâches dans des environnements de développement isolés et peuvent ouvrir des pull requests une fois celles-ci terminées. Elle s’adresse aux équipes qui souhaitent déléguer le travail sur leurs dépôts à des agents, avec des retours et des validations en temps réel.
文心智能体平台AgentBuilder
agents.baidu.com
文心智能体平台AgentBuilder est la plateforme d’agents de Baidu pour créer, gérer et distribuer des agents avec les modèles Wenxin.