Skip to main content
A Guava WebRTC integration has two parts:
  1. A hosted agent that handles the conversation.
  2. Frontend code that dials the agent from the browser using the WebRTC SDK.
Guava agents currently run as long-running worker processes, which Base44 doesn’t support. We recommend writing your agent in TypeScript and deploying it with Guava’s managed deployments, then having Base44 build the frontend.
Guava is planning support for Function-as-a-Service platforms, which will let you host agents directly in Base44.
Just want a voice button on your site? The drop-in widget is a single <script> tag that you can ask Base44 to add to index.html. You’ll still need a deployed agent.

​
Create a TypeScript agent

Install the CLI and log in by following the Quickstart. Then scaffold an inbound TypeScript project.
TypeScript isn’t required, but it keeps your agent in the same language as your Base44 app.

​
Attach the agent to a WebRTC code

Create a WebRTC code. This is the address your Base44 frontend will dial.
In main.ts, attach your agent to the code with listenWebrtc.
main.ts
See the Agent reference to customize what your agent says and does.

​
Test locally

Run your agent, then dial it from the browser at app.goguava.ai/debug-webrtc.

​
Deploy the agent

Deploy your agent so it stays online for your Base44 app.
See the Deployment guide for logs, scaling, and instance tiers.

​
Build the frontend in Base44

Paste a prompt like this into Base44’s chat, replacing grtc-... with your WebRTC code.
Base44 will install the SDK and wire up the call. From there, you can keep iterating in Base44 on the UI, for example passing the signed-in user to your agent with customPayload.
If the call fails to connect and your browser console mentions a Content Security Policy (CSP), Base44’s security settings are blocking the connection to Guava. Contact Base44 support to allow WebRTC connections in your app.