AI News HubLIVE
站内改写1 min read

Show HN: Every Claw Deserves a Face

Nyxclaw is an open-source project that gives AI agents a real-time face and voice. It runs locally without a GPU, offers self-hosted servers with end-to-end encryption, two voice pipelines (OpenAI Realtime and local CPU stack), and supports ARKit blendshapes at 30 FPS.

SourceHacker News AIAuthor: antonios_makro

Nyxclaw — Every claw deserves a face

Every claw

deserves a face.

Give any AI agent a real-time face and voice. Open source, runs on your machine, no GPU required.

App Store Coming soon

Google Play

Get Server

See it in action

Your server. Your data.

NyxClaw server runs on your machine, right alongside your claw, end-to-end encrypted, and cryptographically paired. No cloud, no relay, no telemetry.

🔐

Ed25519 Auth

Device pairing via cryptographic challenge. No passwords over the wire.

🔒

End-to-end WSS

Auto-provisioned Cloudflare Tunnel. No port forwarding or certs.

📱

QR Pairing

Scan to connect. One device at a time. Treat the code like a password.

🏠

Self-hosted

Docker or install script. Your machine, your data, your rules.

Two voice pipelines

Two reference pipelines out of the box — OpenAI Realtime for the cloud voice quality, local CPU stack for total privacy. Swap or extend either one.

OpenAI Voice

▸ Realtime API for STT + TTS

▸ Best voice quality

▸ ~1 GB RAM, 1 core

▸ Requires API key

🖥️ Local Voice CPU

▸ faster-whisper + Silero VAD

▸ Piper VITS ONNX TTS

▸ ~2 GB RAM, 2 cores

▸ No API keys. No cloud. No GPU.

Both pipelines run Wav2Arkit ONNX on CPU — 52 ARKit blendshapes at 30 FPS.

🤗 Model

Supported claws

Add a voice and a face to your claw. Request a claw we might not support yet.

+ Request a claw

Help us feed the claws 🦞