Skip to main content
One thing, three names. In these docs we call your assistant a Digital Twin. You will also see it called an Instance — on the Instance Settings panel, in the admin Instances list, and in your web address (your-instance.praxislxp.com) — and an Institution, which is what our software calls it behind the scenes (in API fields such as institution). All three mean exactly the same thing: one assistant, with its own knowledge, voice, members and settings. Which name you see depends on the screen you are on, not on what the thing is. An Account is different — it is the organisation that owns one or more Digital Twins.
The Developer section covers every programmatic way to connect to a Praxis AI Digital Twin — REST APIs, the JavaScript SDK, web and chat embeds, LMS integrations, voice providers, and the MCP server. New here? Start with Authentication, then pick the integration path that matches what you are building.

​
Choose your integration path

Chat Completions

Fastest path. Point any OpenAI-compatible SDK at a Digital Twin as a Custom LLM — minimal setup, full compatibility.

REST API

Full control. Call the Runtime and Administrator APIs directly to build custom backends and automations.

JavaScript SDK

Embed in your app. Add AI chat, assistants, and Twin actions to your own web platform with the SDK.

Web & Avatar Widgets

Drop-in embed. Add a Twin — or a talking avatar — to any website with a script tag or React component.

LMS Integrations

Deploy in your LMS. Native Canvas, plus D2L, Blackboard, and Moodle via LTI 1.3.

Voice & Avatars

Give it a voice or a face. ElevenLabs, Gemini Live, OpenAI Realtime, and Anam talking avatars.

MCP Server

Connect an LLM stack. Expose your Twin’s context to custom LLM workflows via Model Context Protocol.

Other Services

Extend further. Google Workspace and Stripe billing integrations.

​
Before you start

1

Authenticate

Every integration needs credentials. Review Authentication for API keys, social OAuth, and enterprise SSO.
2

Pick a path

Use the cards above to match your use case — a hosted app, an embed, an LMS, or a custom LLM stack.
3

Build & test

Follow the guide for your path. Each area includes setup steps, examples, and reference material.