Opensource, on-device voice + vision layer for AI agents. Bring any model or coding agent; the whole speech loop (VAD, STT, TTS, barge-in) runs locally. An open alternative to ElevenLabs Agents, Gemini Live, and OpenAI Realtime.
cli open-source opensource opencode tts cursor hermes stt codex voice-assistant conversational-ai openlive voice-cloning local-first voice-ai coding-agents vision-agents openai-realtime claude-code
-
Updated
Aug 27, 2026 - TypeScript