Bodhi Realtime Agent FrameworkBuild Real-Time Voice Agents

TypeScript framework for voice AI applications — supports Google Gemini Live and OpenAI Realtime APIs

Real-Time Voice

Bidirectional audio streaming via a provider-agnostic LLMTransport interface. Supports Google Gemini Live and OpenAI Realtime APIs with server-side turn detection, pluggable STT providers, and sub-500ms latency.

Multi-Agent

Define multiple agents with distinct personas and tool sets. Transfer between them mid-conversation with automatic context preservation.

Function Tools

Inline (blocking) and background (non-blocking) tool execution. Zod schema validation, timeout, cancellation, and abort signals.

Memory

Automatic extraction and persistence of durable user facts across sessions. LLM-powered distillation with configurable triggers.

Observability

Type-safe EventBus and lifecycle hooks for logging, metrics, and debugging. Zero overhead when unattached.

Multimodal

Voice, text input, file upload, and image generation on a single WebSocket connection. Mixed-mode interaction out of the box.