Skip to content
SPECIFICTION
Get listed

OpenTest.AI

opentest.ai

Free plan Self-hosted
Visit opentest.ai
Spec score 7.8 #12 of 21 in AI Test Case Generators

What it is

OpenTest.AI is a self-hosted, open-source project for local-first AI quality checks and portable JSON testing formats. Its six skills include automatic bug fixing, deep quality scans, risk analysis, statistical confidence analysis, smart comparisons, and metrics. The skills run locally without an API key, cloud call, or account, and integrate with clients such as Claude Code, Cursor, Codex CLI, GitHub Copilot Chat, Aider, and Continue.dev. jank_deep scans 12 quality dimensions, while jank_risk follows code blast radius, GenAI smells, user frustration, and business risk. jank_confidence uses test-coverage statistics and estimates the cost and time to close gaps. jank_diff compares APIs, documents, or local files while ignoring timestamps, dynamic IDs, and generated metadata noise. The project analyzes screenshots, network and console logs, and DOM or accessibility trees through 33+ AI testing profiles. It supports bug detection, persona feedback, and prioritized test-case generation. Test cases can be replayed by Playwright, Selenium, Cypress, or a human. The MIT plan is free forever.

Spec sheet

Additional services
The site says jank.ai also offers cloud browser testing, URL monitoring dashboards, autonomous hunt-and-fix loops, and human-eye reviews.Read 1 Oct 2026 · opentest.ai
AI client integrations
The skills work with Claude Code, Cursor, Antigravity, Codex CLI, GitHub Copilot Chat, Aider, Continue.dev, and AGENTS.md-aware tools.Read 1 Oct 2026 · opentest.ai
Auto-fix
jank auto-fix finds bugs in recent changes and can work on code, documents, images, and Office files.Read 1 Oct 2026 · opentest.ai
Bug detection
The open-source project analyzes screenshots, network logs, console logs, and DOM or accessibility trees using 33+ specialized AI testing profiles.Read 1 Oct 2026 · opentest.ai
Confidence analysis
jank_confidence uses statistical test-coverage analysis with t-tests, p-values, and sampling, and estimates the cost and time to close gaps.Read 1 Oct 2026 · opentest.ai
Local operation
The skills are described as pure-local and require no API key, cloud call, or account.Read 1 Oct 2026 · opentest.ai
Metrics
jank_stats reports cumulative tokens, cost, fixes by category, and estimated developer time and money saved.Read 1 Oct 2026 · opentest.ai
Open skills
The site lists six quality-check skills: jank auto-fix, jank_deep, jank_risk, jank_confidence, jank_diff, and jank_stats.Read 1 Oct 2026 · opentest.ai
Portable formats
OpenTest.AI publishes v1 JSON formats for bugs and test cases designed to move between finders, runners, fixers, and humans.Read 1 Oct 2026 · opentest.ai
Product purpose
OpenTest.AI provides local-first AI quality checks and portable JSON formats for AI-era software testing.Read 1 Oct 2026 · opentest.ai
Quality scan
jank_deep performs a full scan across 12 quality dimensions including correctness, security, reliability, performance, maintainability, and testing.Read 1 Oct 2026 · opentest.ai
Risk analysis
jank_risk traces changes across code blast radius, GenAI smells, user frustration, and business risk.Read 1 Oct 2026 · opentest.ai
Runner interoperability
The test-case format can be replayed by Playwright, Selenium, Cypress, or a human.Read 1 Oct 2026 · opentest.ai
Smart diff
jank_diff compares APIs, documents, or local files while ignoring timestamps, dynamic IDs, and generated metadata noise.Read 1 Oct 2026 · opentest.ai
Testing modes
The project supports bug detection, persona feedback, and prioritized test-case generation for pages or flows.Read 1 Oct 2026 · opentest.ai

Plans and prices

Open source · MIT Free free forever MIT licensed · no API key · no cloud call · no account Read 1 Oct 2026 · opentest.ai

Every OpenTest.AI plan and price →

Strong points and limits

Strong points

  • Runs locally without an API key
  • Six quality-check skills
  • Scans 12 quality dimensions
  • Portable v1 JSON formats
  • Works with multiple AI clients

Limits

  • Self-hosted setup is required

Who it suits

It suits developers and teams wanting self-hosted, local AI quality checks without accounts or API keys. It also fits workflows that need portable test cases or compatibility with several AI coding clients.

Verdict

OpenTest.AI focuses on local quality analysis and reusable testing formats rather than a hosted service. Its broad skill set covers detection, analysis, generation, comparison, and reporting, with free MIT licensing.

Where Specifiction places it

Alternatives to OpenTest.AIAll alternatives →