Skip to main content

Welcome

Build AI characters that see, hear, and remember.

Estuary is a platform for creating conversational AI agents with persistent memory, real-time voice, and spatial awareness—deployed across smartglasses, mobile, and web.

Why Estuary?

Most conversational AI treats every session as a blank slate. Estuary doesn't.

Create AI characters that remember users across conversations spanning months. They understand physical environments through world models and respond in real-time. And they scale from prototype to thousands of concurrent users without rearchitecting.

Core Capabilities

CapabilityWhat it means
Persistent MemoryCharacters recall past conversations, user preferences, and relationships over time
Spatial AwarenessWorld models for object detection, depth estimation, and scene understanding
Real-time VoiceSub-second voice interactions with Deepgram STT and ElevenLabs TTS
Cross-platformBuild your character once, deploy everywhere: Unity, Lens Studio, mobile, and web with no additional configuration
Action TriggersAI responses can invoke in-app events, animations, or external integrations
Multi-tenant ScaleOne character definition serves hundreds of concurrent end users with isolated sessions

Quick Overview

The Estuary SDK consists of several core components that work together:

┌─────────────────────────────────────────────────────────────┐
│ Your Lens Studio Project │
├─────────────────────────────────────────────────────────────┤
│ │
│ ┌───────────────────┐ ┌──────────────────┐ │
│ │ EstuaryCredentials│ → │ SimpleAutoConnect│ │
│ │ (API Key, IDs) │ │ (Connection Mgr) │ │
│ └───────────────────┘ └────────┬─────────┘ │
│ │ │
│ ┌────────────────────────┼────────────────┐ │
│ ↓ ↓ ↓ │
│ ┌─────────────────┐ ┌──────────────────┐ ┌───────────┐ │
│ │EstuaryMicrophone│ │ EstuaryCharacter │ │ Action │ │
│ │ (Voice Input) │ │ (AI Connection) │ │ Manager │ │
│ └─────────────────┘ └──────────────────┘ └───────────┘ │
│ │
└─────────────────────────────────────────────────────────────┘


┌───────────────────┐
│ Estuary Server │
│ (WebSocket API) │
└───────────────────┘

Getting Started

Ready to build your first AI-powered Spectacles experience?

Installation Guide

Start with the step-by-step setup guide to install the SDK in your Lens Studio project.

Voice Connection

Learn how to implement real-time voice conversations with AI characters.

Action System

Discover how to trigger scene actions based on AI responses.

Requirements

Before you begin, ensure you have:

  • Estuary Account with API key and Character ID
  • Lens Studio 5.15.x (Tested with Lens Studio 5.15.1+)

Sample Project

The fastest way to get started is to explore the demo project:

estuary-snap-spectacles-demo/
├── Assets/
│ ├── estuary-lens-studio-sdk/ # The SDK
│ │ ├── src/ # Core SDK source
│ │ └── Examples/ # Example scripts
│ ├── Scene.scene # Main scene
│ └── ...
└── ...

The demo includes:

  • Pre-configured SimpleAutoConnect component
  • EstuaryCredentials for API key management
  • Example action handlers
  • Audio input/output setup

Architecture

The SDK is organized into layers:

LayerComponentsPurpose
CoreEstuaryClient, EstuaryConfig, EstuaryEventsLow-level WebSocket communication
ComponentsEstuaryManager, EstuaryCharacter, EstuaryMicrophoneHigh-level Lens Studio integration
ActionsEstuaryActionManager, EstuaryActionsAction parsing and event dispatch
UtilitiesAudioConverterAudio format conversion

Next Steps

  1. Install the SDK in your Lens Studio project
  2. Set up voice connection for real-time conversations
  3. Configure the action system for interactive experiences
  4. Review the API reference for detailed component documentation