voice-agent

agentscope

+1.2k

Build and run agents you can see, understand and trust.

ai-native-callcenter

+134

Self-hosted API-first AI call center: AI talks, code controls the call. AI agents answer every call; humans take over without dropping it. Runs on FreeSWITCH with your SIP trunk and realtime model (OpenAI, Grok, Qwen, Doubao, or any compatible gateway).

mlx-serve

+121

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.

qwen-audio-agent

+71

A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents

hermes-talk

+34

Hermes Talk: realtime duplex voice for Hermes Agent. Rides your ChatGPT or X Premium subscription, no API key needed. OpenAI, Grok, Gemini. Terminal, Discord, dashboard.

VoiceMem

+115

Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.

CyberVerse

+14

Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.

esp32-thinks

+9

A multi-model Muse: personal AI voice assistant on ESP32 - wake word or knob, any OpenAI-compatible brain (STT/chat/TTS mix-and-match), streaming replies, out of the box. Built on muse-gadget-sdk.

ten-vad

+8

Voice Activity Detector (VAD) : low-latency, high-performance and lightweight