Agent Device vs Spur: Testing Tool Comparison

Agent Device and Spur side by side: verified capabilities, integrations, pricing, and limitations, each claim cited to an official source.

SDK examples

One documented example per tool where available.

  • TypeScript
nodejs-api-basic TypeScript Basic usage Not run
Package:
agent-device (version not recorded)
Install:
npm install agent-device
import { createAgentDeviceClient } from 'agent-device';

async function main() {
  const client = createAgentDeviceClient({
    session: 'qa-integration',
    platform: 'ios',
    udid: 'auto',
  });

  try {
    await client.sessions.open();
    await client.command.openApp({ bundleId: 'com.apple.Preferences' });
    await client.command.tapOn({ text: 'Wi-Fi' });
    await client.command.tapOn({ text: 'Other...' });
    await client.command.inputText({ text: 'MyNetwork', into: 'Network Name' });
    await client.command.tapOn({ text: 'Join' });
  } finally {
    await client.sessions.close();
  }
}

await main();

Run: node --experimental-strip-types examples/sdk/client-session.ts

Adapted from official docs

Spur: no approved SDK sample.
Unknown means no documentation was found; it is not the same as unsupported.
FieldScreenshot of the Agent Device homepage Agent DeviceScreenshot of the Spur homepage Spur
Identity
CategoryTestingTesting
VendorCallstackSpur
Product statusactiveactive
SummaryAgent Device is Callstack's open-source command-line tool and MCP server that lets AI coding agents inspect, control, and verify mobile, TV, desktop, and web applications.Spur is a commercial AI QA testing service that runs plain-English test flows against web and native mobile applications.
Product kindFramework, AI testing agentAI testing agent, Testing platform
AI
Uses AI
Supported
Verified 2026-09-26[5]
Supported
Verified 2026-09-26[1][4][5]
AI test generation
Supported
Verified 2026-09-26[5]
Supported
Verified 2026-09-26[4]
AI executes the app
Supported
Verified 2026-09-26[5]
Supported
Verified 2026-09-26[1]
AI generates code only
Unsupported
Null
Verified 2026-09-26[5]
Unsupported
Verified 2026-09-26[1]
Autonomous exploration
Supported
Verified 2026-09-26[5]
Supported
Verified 2026-09-26[1]
Vision-based interaction
Supported
Verified 2026-09-26[6]
Unknown
Not explicitly stated if it uses vision or DOM.
Verified 2026-09-26[1]
Selector-free execution
Supported
Verified 2026-09-26[7]
Supported
Verified 2026-09-26[1]
Adapts to UI changes
Unknown
Verified 2026-09-26[1]
Supported
Verified 2026-09-26[1]
Self-healing
Unknown
Verified 2026-09-26[1]
Supported
Verified 2026-09-26[5]
AI failure analysis
Supported
Verified 2026-09-26[5]
Supported
Verified 2026-09-26[5]
What it tests
Testing typesEnd-to-end, Functional, Regression, ExploratoryEnd-to-end, Functional, Regression, Smoke, Exploratory
TargetsWeb app, Native desktop, Native mobileWeb app, Native mobile
Native desktop testing
Supported
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[1]
Native mobile testing
Supported
Verified 2026-09-26[1]
Supported
Verified 2026-09-26[1]
Browser extension testing
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[1]
Cross-browser testing
Unknown
Verified 2026-09-26[1]
Supported
Verified 2026-09-26[2]
Cross-platform testing
Supported
Verified 2026-09-26[1]
Supported
Verified 2026-09-26[1]
Real device testing
Supported
Verified 2026-09-26[2]
Unknown
Verified 2026-09-26[1]
Multi-tab testing
Unknown
Verified 2026-09-26[1]
Supported
Verified 2026-09-26[13]
iframe testing
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[13]
Canvas testing
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[13]
PDF validation
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[13]
File upload testing
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[13]
File download testing
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[13]
OAuth testing
Unknown
Verified 2026-09-26[1]
Supported
Verified 2026-09-26[1]
Email testing
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[13]
Notification testing
Supported
Verified 2026-09-26[8]
Unknown
Verified 2026-09-26[13]
Video content validation
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[13]
Developer integrations
MCP server
Supported
Verified 2026-09-26[5]
Supported
Verified 2026-09-26[6][7]
VS Code extension
Unknown
Verified 2026-09-26[5]
Unsupported
Uses MCP via GitHub Copilot in VS Code, not a dedicated extension.
Verified 2026-09-26[7]
SDK
Supported
Verified 2026-09-26[3]
Unsupported
Verified 2026-09-26[7]
PR workflow
GitHub
Supported
Verified 2026-09-26[8]
Supported
Integration
Verified 2026-09-26[9]
CI execution
Supported
Verified 2026-09-26[2]
Supported
Integration
Verified 2026-09-26[1]
GitHub PR checks
Unknown
Verified 2026-09-26[2]
Supported
Integration
Verified 2026-09-26[1]
PR-aware test selection
Unknown
Verified 2026-09-26[2]
Supported
Integration
Verified 2026-09-26[10]
Autonomous PR validation
Supported
Verified 2026-09-26[2]
Supported
Integration
Verified 2026-09-26[10]
PR comments
Unknown
Verified 2026-09-26[2]
Unknown
Verified 2026-09-26[10]
Preview deployment testing
Unknown
Verified 2026-09-26[2]
Supported
Verified 2026-09-26[11]
Merge gating
Unknown
Verified 2026-09-26[2]
Supported
Integration
Verified 2026-09-26[1]
Scheduled execution
Unknown
Verified 2026-09-26[2]
Supported
Verified 2026-09-26[12]
Pricing
Pricing
Free
Unknown
Pricing modelsFreeSubscription, Usage-based
Free tierAvailableUnavailable
TrialNot applicableUnknown
Deployment
DeploymentLocal, Self-hostedSaaS
LicenseOpen sourceProprietary
License identifiersMITNot researched
Compatibility
LanguagesJavaScript, TypeScript, Natural languageNatural language
Runner OSWindows, macOS, LinuxNot researched
Target OSWindows, macOS, Linux, iOS, AndroidiOS, Android
Browser enginesNot researchedNot researched
BrowsersNot researchedNot researched
Device modesReal device, Emulator, SimulatorResponsive viewport
Creation and execution
Execution modelOS input, Real device, Emulator, Simulator, HybridHybrid
Authoring methodCode, AI-generated workflow, Autonomous exploration, Imported testsNatural language, AI-generated workflow, Imported tests
Code authoring
Supported
Verified 2026-09-26[3]
Unsupported
Tests are written in natural language.
Verified 2026-09-26[1]
Recorder
Supported
Verified 2026-09-26[4]
Unsupported
Contrasts itself with record-and-play tools.
Verified 2026-09-26[1]
Natural language authoring
Supported
Verified 2026-09-26[5]
Supported
Verified 2026-09-26[1]
Test import
Supported
Verified 2026-09-26[4]
Supported
Verified 2026-09-26[1]
Reusable steps
Supported
Verified 2026-09-26[4]
Supported
Verified 2026-09-26[3]
Parameterized tests
Supported
Verified 2026-09-26[4]
Supported
Verified 2026-09-26[1]
Test data generation
Unknown
Verified 2026-09-26[1]
Supported
Verified 2026-09-26[4]
Fit
AudienceDevelopers, QA engineers, SDETQa 工程师, Developers, Product managers
Company sizeSolo, Startup, SMB, Mid-market, EnterpriseSMB, Mid-market, Enterprise
Use casesRegression testing, Pull request validation, Test generationPull request validation, Regression testing, Release gating, Cross platform testing, Test generation
Validation
Visual regression
Supported
Verified 2026-09-26[8]
Unknown
Verified 2026-09-26[13]
Semantic visual assertions
Supported
Verified 2026-09-26[4]
Unknown
Verified 2026-09-26[13]
Accessibility checks
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[13]
API assertions
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[13]
Database assertions
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[13]
Spelling and grammar checks
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[13]
Dark and light mode testing
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[13]
Performance measurement
Supported
Verified 2026-09-26[8]
Unknown
Verified 2026-09-26[13]
Running
Local execution
Supported
Verified 2026-09-26[1]
Unsupported
Verified 2026-09-26[1]
Headless execution
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[2]
Headed execution
Supported
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[2]
Parallel execution
Supported
Verified 2026-09-26[2]
Supported
Verified 2026-09-26[1]
Test sharding
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[2]
Auto-waiting
Supported
Verified 2026-09-26[4]
Supported
Verified 2026-09-26[14]
Automatic retries
Supported
Verified 2026-09-26[4]
Unknown
Verified 2026-09-26[2]
Network mocking
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[2]
Secrets injection
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[2]
Private network access
Unknown
Verified 2026-09-26[1]
Supported
Verified 2026-09-26[1]
Diagnosis
Screenshots
Supported
Verified 2026-09-26[8]
Supported
Verified 2026-09-26[15]
Video recording
Unknown
Verified 2026-09-26[8]
Supported
Verified 2026-09-26[1]
Execution traces
Supported
Verified 2026-09-26[5]
Unknown
Verified 2026-09-26[15]
Console logs
Supported
Verified 2026-09-26[5]
Supported
Verified 2026-09-26[15]
Network logs
Supported
Verified 2026-09-26[5]
Supported
Verified 2026-09-26[15]
Replay
Supported
Verified 2026-09-26[4]
Unknown
Verified 2026-09-26[15]
Interactive debugging
Supported
Verified 2026-09-26[5]
Unknown
Verified 2026-09-26[15]
Failure grouping
Unknown
Verified 2026-09-26[1]
Unknown
Verified 2026-09-26[15]
Debug artifactsScreenshot, Trace, Console log, Network logScreenshot, Video, Console log, Network log
Enterprise
SSO (SAML)
Unknown
Verified 2026-09-26[10]
Unknown
Verified 2026-09-26[1]
SSO (OIDC)
Unknown
Verified 2026-09-26[10]
Unknown
Verified 2026-09-26[1]
SCIM
Unknown
Verified 2026-09-26[10]
Unknown
Verified 2026-09-26[1]
RBAC
Unknown
Verified 2026-09-26[10]
Supported
Verified 2026-09-26[1]
Audit logs
Unknown
Verified 2026-09-26[10]
Unknown
Verified 2026-09-26[1]
Secrets management
Unknown
Verified 2026-09-26[10]
Unknown
Verified 2026-09-26[1]
Configurable retention
Unknown
Verified 2026-09-26[10]
Supported
Verified 2026-09-26[1]
Private runners
Unknown
Verified 2026-09-26[10]
Unknown
Verified 2026-09-26[1]
On-premises deployment
Supported
Verified 2026-09-26[1]
Unsupported
Verified 2026-09-26[1]
Data residency
Unknown
Verified 2026-09-26[10]
Unknown
Verified 2026-09-26[1]
Training opt-out
Unknown
Verified 2026-09-26[10]
Unknown
Verified 2026-09-26[1]
Operations
Setup difficultylowlow
Maintenance approachManual code, Resilient locatorsSelf-healing, Managed service
Max concurrencynullnull
Reliability mechanismsAuto wait, RetryAuto wait
InterfacesCLI, API, SDK, MCPWeb UI, MCP
Security
CertificationsNot researchedNot researched
Data regionsNot researchedNot researched
Customer data used for trainingNot researchedNot researched
Support
Support channelsDocs, Github issuesSlack, Docs, Email
Support SLANot researchedNot researched
Integrations
IntegrationsBrowserStack, AWS Device Farm, LimrunJira, Linear, Azure DevOps, Slack, GitHub, GitLab