The complete AI dev toolkit for

full-stack Phoenix and Rails

Connect your coding agent and IDE to your running app: database, logs, and UI. Point to any element to reference it. Your agent sees what you see.

Tidewave

A better way to build Phoenix and Rails apps with AI

To get the most from your coding agent, you need to give it the right tools.
The question is how.

Without Tidewave

Multiple tools, multiple configs

Hunt down separate tools for development, browser automation, code review, etc. Configure each. Debug when they clash.

Generic tools

Playwright, Context7, and others work, but they can't see inside your app. So your agent has to fill in the gaps.

Text only

Describe UI elements to the agent: "The button in the header—no, the other header...". Copy and paste stacktraces.

With Tidewave

One install, one config

Coding agent, browser integration, database access, and code review, all in one package. Set up in minutes.

Framework-integrated tools

Trace pages and components to source. Get docs for your exact dependency versions. Run code in your running app.

Text + point and click + vision

Include UI elements in your prompts with a click. Attach screenshots with vision mode. Do more, type less.

Features

Point and click prompting

Want to change something? Click it. Tidewave doesn't just read the DOM, it traces elements back to your source code, forwarding it all to your agent. Learn more

Browser automation

Your coding agent can control your web app through the browser. Think Playwright, but augmented with our framework-aware annotations and diagnostics. Learn more

Vision mode

Your agent captures screenshots to spot visual regressions it would miss from code alone. It can also record videos as proof of work, so your team can verify without re-testing. Learn more

Catch issues before production

Surface client-side errors and run web accessibility reports enhanced with web framework metadata. Give your coding agent the context it needs to identify defects faster and resolve them before you ship. Learn more

UI variants

Your coding agent can propose multiple versions of a page or UI component. Pick your favorite or request further changes, within your web app. Learn more

UI variants are awesome!

Container Toast
1/3 Soft

Deep integration with your web framework

Give your coding agent new tools to access everything your app knows.
Get better results, less back-and-forth. We call this Runtime Intelligence.

Runtime introspection

Give your agents their own REPL to test methods, read logs, and explore APIs.

Access documentation

Pull docs for your exact library versions, not whatever a web search returns.

Query your database

Access your models and tables using your app's existing connection. No additional tools required.

Works with your coding agents and IDEs

You can use any coding agent and IDE with MCP support.

Tidewave enhances Claude Code, making it 2x more accurate and 45% faster on average for full-stack changes

Read our report →
% of accessibility issues solved
Tidewave + Claude Code
0% ↓158s, ↓25.1k tokens
Claude Code
0% ↑290s, ↑27.7k tokens

Pricing

Pro and Teams subscriptions unlock all Tidewave features.

Free

OSS

Connect your editor to Tidewave's Runtime Intelligence through MCP.

Learn more

Tidewave MCP

Runtime introspection

Documentation lookup

Database access

$10/mo

Pro

Design, code, and validate features in the browser alongside your app.

Try it for free

Everything in OSS plus

Point and click prompting

Browser automation

Vision mode

Enhanced accessibility reports

UI variants

$12/user/mo

Teams

Advanced security, support, and control for organizations.

Try it for free

Everything in Pro plus

Enforce settings org-wide

Centralized team billing

Early adopter pricing

Coming soon

Single Sign On (SSO)

Price excludes taxes. Pro's free trial has a limit of 10 prompts and 10 browser agents per month.

Need Help?

If you have questions, don't hesitate to reach out.

How is Tidewave different from Playwright, Cursor Browser?
Tidewave offers the following advantages compared to generic browser tools:
  • Uses your browser: Tidewave uses your existing browser and sessions, making it much easier for the agent to see and debug the same page you are working with.
  • Error handling: Tidewave automatically recognizes error pages and feeds stacktraces, logs, framework metadata to the agent.
  • Vision mode: Tidewave's vision mode includes the ability to record videos with captions, narration, and other bells and whistles for proof of work.
Which coding agents and IDEs do you support?
We support any coding agent and IDE that provide MCP support. This includes Claude Code, OpenAI Codex, OpenCode, VS Code, Cursor, and many more.
What is your data policy?
We log basic request metadata (timestamps, feature used, etc). Prompts are not logged unless you explicitly opt-in.

See our Terms of Service and Privacy Policy.
Do you offer trial plans?
Yes! The Pro plan includes a free trial, no credit card required, with a limit of 20 user messages per month.
Do you offer enterprise plans?
We are working on enterprise plans and we would love your feedback on how to best shape them according to your needs. Please send us an email with your needs.
What are the security risks of running Tidewave?
Tidewave is a MCP server which runs code on your machine. Therefore, you must approve and review tool calls as any other tool call performed by your coding agent. Please read our security guidelines , which includes common concerns and isolation techniques such as Docker support.

Note Tidewave is a development tool and should not run in production.
Is Tidewave open source?
Some components of Tidewave are open source. In particular, we have open sourced the "Runtime Intelligence" component for each supported language/framework, which you can use directly from most AI editors and third party coding agents through the Model Context Protocol (MCP), without a Tidewave subscription. Check out our Organization on GitHub for all supported languages and frameworks.