Screenshot of the TestZeus Hercules homepage
TestZeus Hercules logo

TestZeus Hercules

Active

Hercules is TestZeus's open-source testing agent that executes test cases written in natural language.

Website Docs Pricing Repository
TestZeus Last verified: Partial, 2026-09-26

Overview and fit

Audience

Editorial judgment, not a vendor fact.

Compatibility

Test languages
Natural language Python
Runner operating systems
Windows Linux macOS
Target operating systems
Windows macOS Linux
Browser engines
Chromium Firefox WebKit
Browsers
Chrome Edge Firefox Safari
Device modes
Emulator Responsive viewport

What it tests

Product kind
AI testing agent
Testing types
End-to-end, Functional, Regression, API, Visual, Accessibility
Targets
Web app, API
Use cases
Regression testing, Release gating, Test generation

Classification lists positively established capabilities. Absence from a list does not mean lack of support.

Creation and execution

Authoring methods
Natural language, AI-generated workflow
Execution models
Browser protocol
Deployment
Local, SaaS, Self-hosted
License
Open source, Proprietary

Capabilities

AI

Capability Status Details
Uses AI Supported Supported
AI test generation Supported Supported
AI executes the app Supported Supported
AI generates code only Unsupported Unsupported
Autonomous exploration Unknown Unknown
Vision-based interaction Supported Supported
Selector-free execution Supported Supported
Adapts to UI changes Supported Supported
Self-healing Supported Supported
AI failure analysis Unknown Unknown

Developer integrations

Capability Status Details
MCP server Supported Supported
VS Code extension Unknown Unknown
SDK Supported Supported

PR workflow

Capability Status Details
GitHub Unknown Unknown
CI execution Supported Supported
GitHub PR checks Unknown Unknown
PR-aware test selection Unknown Unknown
Autonomous PR validation Unknown Unknown
PR comments Unknown Unknown
Preview deployment testing Unknown Unknown
Merge gating Unknown Unknown
Scheduled execution Supported Supported

Creation and execution

Capability Status Details
Code authoring Supported Supported

Custom code
Recorder Unknown Unknown
Natural language authoring Supported Supported
Test import Unknown Unknown
Reusable steps Supported Supported
Parameterized tests Unknown Unknown
Test data generation Unknown Unknown

What it tests

Capability Status Details
Native desktop testing Unknown Unknown
Native mobile testing Unknown Unknown
Browser extension testing Unknown Unknown
Cross-browser testing Supported Supported
Cross-platform testing Unknown Unknown
Real device testing Unknown Unknown
Multi-tab testing Unknown Unknown
iframe testing Supported Supported
Canvas testing Unknown Unknown
PDF validation Unknown Unknown
File upload testing Supported Supported
File download testing Unknown Unknown
OAuth testing Unknown Unknown
Email testing Unknown Unknown
Notification testing Unknown Unknown
Video content validation Unknown Unknown

Validation

Capability Status Details
Visual regression Supported Supported
Semantic visual assertions Supported Supported
Accessibility checks Supported Supported
API assertions Supported Supported
Database assertions Unknown Unknown
Spelling and grammar checks Unknown Unknown
Dark and light mode testing Unknown Unknown
Performance measurement Unknown Unknown

Running

Capability Status Details
Local execution Supported Supported
Headless execution Supported Supported
Headed execution Supported Supported
Parallel execution Supported Supported
Test sharding Unknown Unknown
Auto-waiting Unknown Unknown
Automatic retries Unknown Unknown
Network mocking Unknown Unknown
Secrets injection Unknown Unknown
Private network access Unknown Unknown

Diagnosis

Capability Status Details
Screenshots Supported Supported
Video recording Supported Supported
Execution traces Supported Supported
Console logs Unknown Unknown
Network logs Supported Supported
Replay Unknown Unknown
Interactive debugging Unknown Unknown
Failure grouping Unknown Unknown

Enterprise

Capability Status Details
SSO (SAML) Supported Supported
SSO (OIDC) Unknown Unknown
SCIM Supported Supported
RBAC Unknown Unknown
Audit logs Unknown Unknown
Secrets management Unknown Unknown
Configurable retention Supported Supported
Private runners Supported Supported
On-premises deployment Unknown Unknown
Data residency Unknown Unknown
Training opt-out Unknown Unknown

Maintenance, reliability, and debugging

Setup difficulty
Low
Maintenance approaches
Self-healing, Ai regeneration
Maximum concurrency
15
Debug artifacts
Screenshot, Video, Network log, Html report, Junit
Reliability mechanisms
Self-healing
Interfaces
CLI, SDK, MCP

Pricing

Unknown

Models: Subscription, Usage-basedFree tier: UnavailableTrial: Available

Not yet verified · Official pricing page

Security and deployment

Certifications
None recorded
Data regions
Unknown
Data retention
Unknown
Customer data used for training
Unknown

Support

Channels
Slack, Docs, Dedicated engineer
Support SLA
Unknown

SDK code samples

python-quickstart Python Testing Not run
Package:
testzeus-hercules (version not recorded)
Install:
pip install testzeus-hercules
pip install testzeus-hercules

Run: testzeus-hercules

Official docs

Sources and verification

  1. 1TestZeus | AI Test Automation for Salesforce · Official website · TestZeus · retrieved 2026-09-26

    Supports 7 claims · Vendor documented, high confidence · verified 2026-09-26

    • Adapts to UI changes
    • Maintenance approach
    • Product status
    • Reliability mechanisms
    • Self-healing
    • Tool
    • Vendor

    TestZeus adapts to changing UIs and data, self-healing locators and flows automatically

    TestZeus | AI Test Automation for Salesforce

  2. 2testzeus-hercules/README.md at main · test-zeus-ai/testzeus-hercules · GitHub · Official repository · TestZeus · retrieved 2026-09-26

    Supports 87 claims · Vendor documented, high confidence · verified 2026-09-26

    • Accessibility checks
    • AI executes the app
    • AI failure analysis
    • AI generates code only
    • AI test generation
    • API assertions
    • Authoring method
    • Auto-waiting
    • Automatic retries
    • Autonomous exploration
    • Autonomous PR validation
    • Browser engines
    • Browser extension testing
    • Browsers
    • Canvas testing
    • CI execution
    • Code authoring
    • Code samples
    • Console logs
    • Cross-browser testing
    • Cross-platform testing
    • Dark and light mode testing
    • Database assertions
    • Debug artifacts
    • Deployment
    • Device modes
    • Email testing
    • Execution model
    • Execution traces
    • Failure grouping
    • File download testing
    • File upload testing
    • GitHub
    • GitHub PR checks
    • Headed execution
    • Headless execution
    • iframe testing
    • Integrations
    • Interactive debugging
    • Interfaces
    • Languages
    • License
    • License identifiers
    • Local execution
    • MCP server
    • Merge gating
    • Multi-tab testing
    • Native desktop testing
    • Native mobile testing
    • Natural language authoring
    • Network logs
    • Network mocking
    • Notification testing
    • OAuth testing
    • Parameterized tests
    • PDF validation
    • Performance measurement
    • PR comments
    • PR-aware test selection
    • Preview deployment testing
    • Private network access
    • Product kind
    • Real device testing
    • Recorder
    • Replay
    • Reusable steps
    • Runner OS
    • Screenshots
    • SDK
    • Secrets injection
    • Selector-free execution
    • Semantic visual assertions
    • Setup difficulty
    • Spelling and grammar checks
    • Summary
    • Support channels
    • Target OS
    • Targets
    • Test data generation
    • Test import
    • Test sharding
    • Uses AI
    • Video content validation
    • Video recording
    • Vision-based interaction
    • Visual regression
    • VS Code extension

    Gherkin In, Results Out... Guided test creation (--guided or --test) uses the LiteLLM-backed Gherkin generator

    Full Playwright access | Direct control over browser, page, and context.

    pip install testzeus-hercules

    video recordings, screenshots per event, and network logs in the proofs folder

    Approach 1: Using PyPI Package... Approach 2: Using Docker

    Mobile Device Emulation

    Testing modern web applications can be difficult

    Gherkin In, Results Out... Execute custom Python scripts directly from Gherkin tests

    Hercules is the world's first open-source testing agent

    Running Hercules on a Windows Machine

    Hercules is the world's first open-source testing agent, built to handle the toughest testing tasks so you don't have to.

    Join us at our Slack to connect with the community, ask questions, and contribute.

    Testing modern web applications

  3. 3Pricing | TestZeus · Official pricing · TestZeus · retrieved 2026-09-26

    Supports 26 claims · Vendor documented, high confidence · verified 2026-09-26

    • Audience
    • Audit logs
    • Certifications
    • Company size
    • Configurable retention
    • Customer data used for training
    • Data regions
    • Data residency
    • Free tier
    • Max concurrency
    • On-premises deployment
    • Parallel execution
    • Pricing
    • Pricing models
    • Private runners
    • RBAC
    • Scheduled execution
    • SCIM
    • Secrets management
    • SSO (OIDC)
    • SSO (SAML)
    • Support SLA
    • Testing types
    • Training opt-out
    • Trial
    • Use cases

    Unlimited users for QA, admins, product, developers, release, and business stakeholders

    Private runners available

    For large Salesforce teams, ISVs, and consulting firms scaling autonomous QA across orgs, teams, and release cycles.

    Free trial

    15 parallel Scenario Runs included

    $800/mo includes 800 Scenario Runs. 1,365 additional runs × $0.99.

    Best for growing Salesforce teams running release validation, scheduled testing, and regression suites.

Hands-on tested: no (documentation research only) · Content updated 2026-09-26