"A box that sits in the user's home or office, runs without internet access, understands Mongolian, and acts as their personal AI employee."
Status: Vision / Long-term Roadmap
Date: 2026-03-30
The GoClaw Appliance is a box that sits in the user's home or office, runs without internet access, understands Mongolian, and acts as their personal AI employee. This page is the vision and long-term roadmap for it.
Alexa, Google Home, Apple HomePod — the world's most famous AI assistants:
❌ Do not understand Mongolian
❌ Send all your conversations to Amazon/Google servers
❌ Do not work if the internet is down
❌ Cannot be customized or extended (black box)
❌ Require subscriptions and suffer from cloud lock-in
✅ Native support for the Mongolian language
✅ Your voice recordings never leave your premises
✅ Offline-first — works even without internet access
✅ Leverages all GoClaw SOPs, tools, and memory
✅ One-time purchase, no subscription fees
flowchart TD
subgraph BOX["GoClaw One — Matte Black / White Cylinder (iPhone height)"]
LED["<b>LED Ring</b><br/>12x RGB status indicator"]
LOGO["<b>GoClaw Logo</b>"]
MIC["<b>Mic Array</b><br/>6-mic ReSpeaker (360° wake word)"]
SPK["<b>Speaker</b><br/>360° full-range sound"]
PORTS["<b>Ports</b><br/>USB-C Power · Gigabit Ethernet"]
LED --- LOGO --- MIC --- SPK --- PORTS
end
| Segment | Use Case | Benefits |
|---|---|---|
| Enterprise | Office AI assistant in meeting rooms | Fetch GitLab reports and query DBs via voice commands |
| Family | Mongolian smart home voice assistant | Weather, schedules, and reminders |
| Developers | Local AI dev environment | Perform code reviews and git operations via voice commands |
| Government | Classified/secure environments | Air-gapped deployment, zero data leaks |
flowchart TD
subgraph HW["GoClaw One Hardware Stack (BOM: $120-150 · Retail: $299-399)"]
direction LR
PROC["<b>PROCESSING</b><br/>Intel N100 / ARM (mini PC SBC)<br/>RAM: 16GB LPDDR5<br/>Storage: 128GB NVMe (OS + models)"]
IN["<b>AUDIO INPUT</b><br/>ReSpeaker 6-mic Array (360° wake word)<br/>Echo cancellation built-in"]
OUT["<b>AUDIO OUTPUT</b><br/>HiFiBerry DAC+ / Class D amplifier<br/>2x 2.5 in full-range speaker"]
CONN["<b>CONNECTIVITY & STATUS</b><br/>Gigabit Ethernet · WiFi 6 · Bluetooth 5.0<br/>RGB LED ring (12 LEDs — WS2812B)"]
end
flowchart TD
L4["<b>LAYER 4: MEMORY & SKILLS</b><br/>SQLite (local, encrypted) · GoClaw SOP engine · GoClaw skill registry"]
L3["<b>LAYER 3: INTELLIGENCE</b><br/>GoClaw binary (single static binary) · Ollama (offline LLM — qwen2.5:7b) · Cloud API fallback (Gemini/Claude)"]
L2["<b>LAYER 2: VOICE PIPELINE</b><br/>Wake word: OpenWakeWord 'Hey GoClaw' · STT: Whisper (faster-whisper, small) · TTS: Piper TTS (Mongolian model)"]
L1["<b>LAYER 1: OS</b><br/>Custom Linux image (LinuxKit / Buildroot) · Kernel 6.x + network + audio subsystem only · Boot time: < 5 sec (NVMe)"]
L4 --> L3 --> L2 --> L1
flowchart TD
SPEAK["User speaks"] --> WAKE["<b>Wake word</b><br/>100% local"]
WAKE --> STT["<b>Whisper STT</b><br/>100% local, ~0.5-1 sec"]
STT --> NET{"Is there Internet?"}
NET -->|YES| CLOUD["<b>Gemini / Claude</b><br/>Fast, high-quality"]
NET -->|NO| LOCAL["<b>Local Ollama</b><br/>Slower, offline"]
CLOUD --> GC["<b>GoClaw</b><br/>SOP, tools, memory"]
LOCAL --> GC
GC --> TTS["<b>Piper TTS</b><br/>100% local"]
TTS --> OUT["Speaker speaks response"]
This is the largest technical hurdle. Let's list them honestly.
Current Status:
Whisper large-v3 → Mongolian ~60-70% accuracy
For smaller models (tiny/small) → even lower
Technical terms and regional dialects → weak
Proposed Mitigation:
1. Expand the Common Voice MN dataset (community-driven)
2. Fine-tune Whisper small on Mongolian data
3. Inject domain vocabulary bias (GoClaw commands)
Current Status:
Piper TTS → No Mongolian voice model available
Google/Azure TTS → Mongolian models exist (cloud-only)
XTTS-v2 zero-shot → Not optimized for Mongolian
Proposed Mitigation:
1. Collect 10+ hours of high-quality Mongolian audio/text dataset
2. Train a Mongolian model on Piper VITS
3. Interim solution: Google/Azure TTS (online mode)
basic fallback voice (offline mode)
"Hey GoClaw" Mongolian pronunciation:
→ OpenWakeWord custom model (~30 min of training data is sufficient)
→ Personal mode — customize with the user's own voice
→ Community wake word — covering multiple accents and speakers
[ ] GoClaw static binary (CGO-free, modernc/sqlite)
[ ] Ollama + GoClaw on an Intel N100 Mini PC
[ ] Whisper tiny/base Mongolian test
[ ] USB mic + speaker prototype
[ ] Detect "hey goclaw" wake word
[ ] LED ring status indicator
Milestone: A desk-friendly demo prototype
[ ] Collect Mongolian STT dataset (community effort)
[ ] Whisper small → Mongolian fine-tuning
[ ] Mongolian TTS voice model (Piper)
[ ] Custom wake word model
[ ] Integrate hybrid cloud/offline routing into GoClaw
[ ] Extend tool_voice_input.go
[ ] PCB design (Intel N100 / CM4 based)
[ ] 3D print enclosure prototype
[ ] Integrate ReSpeaker 6-mic array
[ ] Speaker + amplifier tuning
[ ] Custom Linux OS image (LinuxKit/Buildroot)
[ ] Secure boot + OTA update
Milestone: 10-20 hand-assembled prototypes
[ ] 10-50 pilot users (Mongolian companies)
[ ] Privacy audit (certify that all data remains strictly local)
[ ] Feedback → iterate
[ ] Establish pricing model ($299 target)
Milestone: Proven, user-accepted appliance in real environments
[ ] Manufacturing partner
[ ] B2B sales targeting Mongolian organizations
[ ] Open source hardware design (CC BY-SA)
Milestone: Full market release
| Alexa Echo | Google Home | Humane Pin | GoClaw One | |
|---|---|---|---|---|
| Mongolian language | ❌ | ❌ | ❌ | ✅ |
| Privacy | ❌ Cloud | ❌ Cloud | ⚠️ | ✅ 100% Local |
| Offline | ❌ | ❌ | ❌ | ✅ hybrid |
| Customizable SOP | ⚠️ | ⚠️ | ❌ | ✅ |
| Enterprise | ❌ | ❌ | ❌ | ✅ |
| Open source | ❌ | ❌ | ❌ | ✅ |
| Price | $50-250 | $30-150 | $699+sub | $299 target |
🔴 HARD — Critical Hurdles:
→ Mongolian TTS dataset (10+ hours of high-quality audio)
→ Mongolian STT accuracy for technical terminology
→ Keeping hardware costs within a $150 BOM while ensuring quality
Proposed Mitigation:
→ Dialects/accent variation in wake word detection
→ Offline LLM quality (limitations of 7B models)
→ OTA update security
🟢 RESOLVED — Already Available:
→ GoClaw static binary compilation works
→ Ollama fallback (fallback.go is ready)
→ SOP + memory engines are ready
→ Hybrid routing is supported
→ tool_voice_input.go base is ready
STT: OpenAI Whisper (MIT)
TTS: Piper TTS (MIT)
Wake word: OpenWakeWord (Apache 2.0)
LLM: Ollama + Llama/Qwen (MIT/Apache)
OS: Linux + LinuxKit (GPL/Apache)
Core: GoClaw (proprietary; binary-use license)
Hardware design: CC BY-SA — schematics are publicly open
"A Mongolian-language, privacy-first, offline-capable AI assistant — in your room, on your desk, heard by no one else."
Journey started: 2026-03-30
Recorded as one of the dreams of the GoClaw project.