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: 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

┌──────────────────────────────────────────────────────────────────────┐
│ Your Application │
├──────────────┬───────────────┬─────────────┬────────────────────────┤
│ Web │ Lens Studio │ Unity │ REST API / cURL │
│ SDK │ SDK │ SDK │ │
└──────┬───────┴───────┬───────┴──────┬──────┴───────────┬────────────┘
│ │ │ │
▼ ▼ ▼ ▼
┌──────────────────────────────────────────────────────────────────────┐
│ Estuary Platform │
│ ┌──────────────┐ ┌───────────┐ ┌───────────────────┐ │
│ │ Gateway │ │ Workers │ │ Memory + Knowledge│ │
│ │ (Socket.IO + │ │ STT→LLM │ │ Graph (PostgreSQL │ │
│ │ REST API) │ │ →TTS │ │ + pgvector) │ │
│ └──────────────┘ └───────────┘ └───────────────────┘ │
└──────────────────────────────────────────────────────────────────────┘

Getting Started

Quickstart

Create a character and start a conversation in under 5 minutes.

REST API Reference

Manage characters, conversations, and memory programmatically.

Web SDK

Build web-based voice and text experiences.

Lens Studio SDK

Build conversational AI for Snap Spectacles.

Unity SDK

Build AI characters for Unity games and AR/VR apps.

Requirements

Before you begin, ensure you have:

  • Estuary Account with an API key (sign up)

Architecture

The platform is organized into layers:

LayerComponentsPurpose
GatewayFastAPI + Socket.IOWebSocket connections, authentication, audio streaming, REST API
WorkersSTT, LLM, TTS pipelineStateless request processing with streaming responses
MemoryPostgreSQL + pgvectorPersistent memory, knowledge graph, entity extraction
InfrastructureRedis, LiveKitJob queue, pub/sub, WebRTC voice

See Platform Overview for details.

Next Steps

  1. Create your first character with the quickstart guide
  2. Explore the REST API for programmatic access
  3. Choose an SDK for your target platform
  4. Learn how memory works across conversations