Connect your AI to Boosthis

One connection. Whichever assistant you already work with.

Boosthis measures how your project really behaves for real users — twelve languages, in the five places they run. Connecting your AI assistant to Boosthis lets it read those measurements: what is slow, what is risky, what changed, and what to do about it. Instead of guessing from the code in front of it, your assistant works from what your running project is actually doing.

The languages you writeJavaScript / TypeScript, Python, Java, Go, PHP, C# / .NET, Ruby, Dart (Flutter), Swift, Kotlin (Android), Rust and Elixir

…and the places that code runsphone apps, browser pages, back-end servers, Bun and edge functions

Works with the assistants you already use

Boosthis connects over the standard tool-connection protocol (MCP), so it works with any assistant that supports it:

• Replit
• Claude
• Cursor
• ChatGPT
• GitHub Copilot
• VS Code
• Windsurf
• Gemini
• and others

No assistant is treated differently: they all read the same data through the same connection.

What a connected assistant can see

• Your projects' performance measurements, issues and suggested fixes.
• Nothing else. The connection is read-only for everything Boosthis measures and serves — your assistant can look, never change a setting, a key, a measurement or a rule. What it can add is its own word: a note of a change it made or plans to make, a promise you asked it to remember, or a report of how it fixed a crash, for a person at Boosthis to review. Each is kept apart from what Boosthis measured.
• No source code and no personal data: everything Boosthis stores passes a strict privacy guard first, described in our Privacy Policy.

How a developer starts

The first three steps happen in your browser: an AI cannot create your account or your key for you.

1. Create an account, confirm your email address with the code we send, and choose a plan or start the trial.
2. Create a project key in the dashboard. It is shown once, so copy it straight away.
3. Open that key's Setup page and pick the AI tool you use.
4. Paste the message it gives you into the AI that works on your project's code, not a separate chat that cannot see it. From there your AI follows Boosthis's private setup guide.
5. Connect your AI to Boosthis. If your tool offers to sign in to Boosthis, that is enough: choose the project and approve. Otherwise an AI that can edit your project's files usually adds the connection itself, and one that can't hands you the line to add in your tool's settings. The Setup page shows that line too. Some tools need a reload before they see a new connection.
6. Let your AI install the kits (one for each language the project runs in, all on the same key), then run the project. Once each kit checks in, readings start to appear in your dashboard as the project is used, and your AI can read them through the connection.

Two common detours:

• If you lose the key before copying it, the dashboard can issue a new one for the same project, and anything already set up keeps working.
• If your AI tool cannot add a connection at all, the kits can still be installed and the dashboard still shows the readings. Only asking your AI about them needs the connection.