#voice-ai

Black-box LiveKit voice agent testing: real WebRTC/SIP calls with an AI caller. Catch barge-in, noise, quiet-mic, and latency failures that text pytest misses. Forensic reports + MCP + lks CLI — no agent code changes.

An open-source debugger for voice agent workflows

Voice driven secure workstream management for Claude Code and Codex

Personalized AI radio agent pipeline: memory-aware dual-host dialogue, multi-provider LLMs, ElevenLabs TTS, and live audio rendering.

Open-source multilingual evaluation toolkit for conversational AI agents.

Local-first AI cognitive operating system with memory, vision, voice, PDF intelligence, CCTV analysis, temporal replay, and agent workflows.

Fully local AI companion with dual-agent evaluation, voice pipeline, screen vision and tool use. No cloud APIs.

An open-source AI workflow platform for speech transcription, LLM-powered processing, and interactive transcript chat using any OpenAI-compatible API.

Browser voice agent that books appointments by talking — built on the AssemblyAI Voice Agent API. Temp-token auth, inline agent config, client-side (simulated) tools.

AI Voice Agent with Live Monitoring, WebRTC Supervisor Takeover, and Twilio Warm Transfer. Built using LiveKit, Next.js, FastAPI, OpenAI, and Deepgram.

Voice-first, agent-readable YouTube research and content planning SaaS built with Next.js, Supabase, OpenAI, Firecrawl, and Apify.

Luminary — voice-first deep-research agent. Talk to it, it runs a multi-phase pipeline (query analysis → study planning → iterative source-grounded research → claim validation → synthesis) and reads the result back. Google ADK + Gemini + OpenAI o4-mini + ElevenLabs on Cloud Run.