Added Nov 5, 2026
Shiplight AI
Freemium · $60/moEnd-to-end tests written and maintained by your coding agent
What is Shiplight AI?
Shiplight AI lets coding agents such as Claude Code, Cursor and Codex write end-to-end tests by walking through your app in a real browser over MCP. Tests are stored as readable YAML in the repo and heal themselves when the UI changes, which suits teams shipping quickly.
You install Shiplight's skills and MCP server into your coding agent with one command. The agent describes user actions in plain-English YAML, which you can review in a pull request or tune in a local debugger, and an AI fixer repairs tests that self-healing cannot.
Tests run locally with one command or on Shiplight-hosted CI runners, with results posted on the pull request. Shiplight says its runners are cheaper per minute than GitHub Actions. Every plan has all features, and you can bring your own LLM key or run on your own infrastructure.
Features
- Agent-authored E2E tests
- Browser MCP server
- Self-healing tests
- YAML tests in your repo
- Hosted CI runners
Tags
Releases
+ Submit new release- Listed
Shiplight AI was added to the directory.
Organization
Shiplight AI
Listed by kitio.ai · unverified owner
Pricing
- Pricing model
- Freemium
- Paid options from
- $60/mo
- Billing frequency
- Monthly
Shiplight AI plans
Free
Free
- $10 signup credit
- Up to 5 members
- 30-day artifact retention
Pro
$60/mo
- $60 monthly credit
- Pay as you go beyond credit
- Up to 25 members
- 90-day retention
Enterprise
Contact sales
- Volume pricing
- SSO and SOC 2
- Dedicated CSM
Prices in USD, checked Nov 5, 2026. Plans change often, so confirm on the Shiplight AI site.Official pricing
Sponsored
Your AI tool here
A Featured launch puts your tool in this spot and on the home page for a week.
Top Shiplight AI alternatives
View allCoding
AI testing agent that checks AI-generated code from your IDE
Coding
Error and performance monitoring with an AI debugging agent
Coding
Free open-source editor with built-in AI agents for coding
Coding
Up-to-date library docs for AI coding agents via MCP
Compare Shiplight AI
If you liked Shiplight AI
Microsoft's MCP server that gives AI agents a real browser
FreeCoding2 views1 clicks to the websiteMade in United StatesTestMu AI's test agent that writes tests from plain English
FreemiumCodingMade in United States
Pros and cons
Pros
- Works with Claude Code, Cursor and Codex
- Readable tests reviewed in PRs
- All features on the free plan
Cons
- Usage beyond credit is metered
- Free plan keeps artifacts only 30 days
- Best suited to teams already using coding agents
Prompts & results
No prompts yet. Add your own prompt and output to help others use this tool.
Share a prompt
Reviews
Q&A
What is Shiplight AI?
Shiplight AI lets coding agents such as Claude Code, Cursor and Codex write end-to-end tests by walking through your app in a real browser over MCP. Tests are stored as readable YAML in the repo and heal themselves when the UI changes, which suits teams shipping quickly.
Which coding agents does Shiplight AI support?
It installs into Claude Code, Cursor, Codex, VS Code and Antigravity, and works with other MCP clients.
Can I use my own LLM key with Shiplight AI?
Yes. Every plan, including the free one, allows bringing your own LLM key and running on your own infrastructure.
How much does Shiplight AI cost?
Shiplight AI is freemium, with paid plans from $60/mo.
Is there a free version of Shiplight AI?
Yes. Shiplight AI has a free plan, and paid plans add more usage and features.
What are the main features of Shiplight AI?
Agent-authored E2E tests, Browser MCP server, Self-healing tests, YAML tests in your repo, Hosted CI runners.
Who makes Shiplight AI?
Shiplight AI is made by Shiplight AI.
What are the best alternatives to Shiplight AI?
Popular alternatives include TestSprite, Sentry, Visual Studio Code.