AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
Connect to a LiveKit room, publish your camera and microphone, and receive the agent greeting
AI summary · website content
Developer toolsVue · HTMLGitHub @meyer1994OnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
meyer1994/livekit
Translation pending
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
This is the smallest local setup: a LiveKit server and a Python agent started by
Docker Compose. The agent's dependencies are managed with uv and pinned in
agent/uv.lock.
The agent uses OpenAI's Realtime API, so provide an OpenAI API key before
starting:
The agent registers with LiveKit and waits for a room job. Each connection uses
a simple AgentSession with OpenAI's gpt-4o-mini-transcribe for speech-to-text,
gpt-4.1-mini for replies, and gpt-4o-mini-tts with the marin voice for
speech output. The assistant is helpful, cheerful, and concise.Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
This is the smallest local setup: a LiveKit server and a Python agent started by
Docker Compose. The agent's dependencies are managed with uv and pinned in
agent/uv.lock.
The agent uses OpenAI's Realtime API, so provide an OpenAI API key before
starting:
The agent registers with LiveKit and waits for a room job. Each connection uses
a simple AgentSession with OpenAI's gpt-4o-mini-transcribe for speech-to-text,
gpt-4.1-mini for replies, and gpt-4o-mini-tts with the marin voice for
speech output. The assistant is helpful, cheerful, and concise.Read the full README ↗