Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Google Home mini "jailbreak" for conversational AI agents
| Date | Stars |
|---|---|
| 2026-07-31 | 264 |
| 2026-08-06 | 264 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Onju Voice v2 (OnjuClaw) 🍐🦞
Enable multiple "Google Home" speakers to connect to your Mac Mini for talking to your agent(s).
This repo consists of:
* An async server pipeline handling ASR -> TTS from multiple devices using any LLM or agent platforms like OpenClaw 🦞
* Hardware designs for a drop-in replacement PCB to the original Google Nest Mini (2nd gen), using the ESP32-S3 for audio processing and WiFi connectivity ([order link](https://www.pcbway.com/project/shareproject/Onju_Voice_d33625a1.html))
> This is an upgraded version of [onju-voice](https://github.com/justLV/onju-voice) as DEMO'd [here](https://x.com/justLV/status/1681377298308820992?s=20)!.
<img src="images/header_white.jpg" width="960">
## What's new in v2
* **Agentic backend** 🦞 -- delegate conversation history, session management, and tool execution to an [OpenClaw](https://github.com/openclaw) gateway for centralized, multi-device orchestration
* **Opus compression** -- 14-16x downstream compression (server to speaker) for better audio quality over WiFi
* **Streaming-ready architecture** -- designed for sentence-level TTS streaming and agentic tool-calling loops
* **Modular async pipeline** -- replaced the monolithic server with a pluggable architecture for ASR, LLM, and TTS backends etc.
* **Any LLM** -- works with any OpenAI-compatible API (Ollama, mlx_lm, Gemini, OpenRouter, Claude, etc.)
* **Pluggable TTS** -- ElevenLabs (recommended) or local via [mlx-audio](https://github.com/lucasnewman/mlx-audio) for fully offline operation
* **Silero VAD** -- server-side voice activity detection with configurable thresholds, replacing webrtcvad
* **VAD-aware interruption** -- tap to interrupt playback and start speaking immediately
* **M5 Echo support** -- get started with a [$13 dev kit](https://shop.m5stack.com/products/atom-echo-smart-speaker-dev-kit) instead of ordering a custom PCB ([battery base](https://shop.m5stack.com/products/atomic-battery-base-200mah))
* **One-command flashing** -- `./flash.sh` handles compilation, WiFi credential generation (from macOS Keychain), and upload. No Arduino IDE or manual configuration required
## Supported devices
| | Onjuino (custom PCB) | M5Stack ATOM Echo |
|---|---|---|
| **Board** | ESP32-S3 | ESP32-PICO-D4 |
| **Interaction** | Capacitive touch: tap to start (uses VAD to end) | Physical button: hold to talk |
| **Mic** | I2S (INMP441) | PDM (SPM1423) |
| **Speaker** | MAX98357A, 6 NeoPixel LEDs | NS4168, 1 SK6812 LED |
| **PSRAM** | Yes (2MB playback buffer) | No (smaller buffers) |
| **Audio upstream** | mu-law 16kHz UDP (16 KB/s) | mu-law 16kHz UDP (16 KB/s) |
| **Audio downstream** | Opus 16kHz TCP (~1.5 KB/s) | Opus 16kHz TCP (~1.5 KB/s) |
Both targets use the same network protocol and connect to the same server. See the [M5 Echo README](m5_echo/README.md) for hardware-specific details.
## Architecture
```
ESP32 Device Server Pipeline
┌──────────────────────────────┐ ┌──────────────────────────────────────┐
│ Mic > I2S RX > mu-law =======UDP 3000===> mu-law decode > VAD > ASR │
│ │ │ │
│ Speaker < I2S TX < Opus <===TCP 3001<=== Opus encode < TTS < LLM │
└──────────────────────────────┘ └──────────────────────────────────────┘
```
**Why mu-law upstream:** Stateless sample-by-sample encoding (~1% CPU), zero buffering latency. ASR models handle the quality fine.
**Why Opus downstream:** Human ears need better quality than ASR, and Opus decoding is easier for an ESP32. Opus gives 14-16x compression vs mu-law's 2x, and TCP ensures reliable ordered delivery for the stateful codec.
### Device discovery
1. ESP32 boots and joins WiFi
2. Sends multicast announcement to `239.0.0.1:12345` with hostname, git hash, and PTT flag
3. Server discovers device and connects to its TCP server on port 3001
4. ESP32 learns server IP from the TCP connection and staExcerpt of 13,242 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:353a7660661dbc96, llm:description: 'Google Home mini "jailbreak" for conversational AI agents'
matched fp:353a7660661dbc96, llm:description: 'Google Home mini "jailbreak" for conversational AI agents'