Aodhan Collins
af6b7bd945
feat: upgrade voice pipeline — MLX Whisper STT (20x faster), Qwen3.5 MoE LLM, fix HA tool calling
...
- Replace faster-whisper with wyoming-mlx-whisper (whisper-large-v3-turbo, MLX Metal GPU)
STT latency: 8.4s → 400ms for short voice commands
- Add Qwen3.5-35B-A3B (MoE, 3B active params, Q8_0) to Ollama — 26.7 tok/s vs 5.4 tok/s (70B)
- Add model preload launchd service to pin voice model in VRAM permanently
- Fix HA tool calling: set commands.native=true, symlink ha-ctl to PATH
- Add pipeline benchmark script (STT/LLM/TTS latency profiling)
- Add service restart buttons and STT endpoint to dashboard
- Bind Vite dev server to 0.0.0.0 for LAN access
Total estimated pipeline latency: ~27s → ~4s
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-13 18:03:12 +00:00
Aodhan Collins
6a0bae2a0b
feat(phase-04): Wyoming Satellite integration + OpenClaw HA components
...
## Voice Pipeline (P3)
- Replace openWakeWord daemon with Wyoming Satellite approach
- Add Wyoming Satellite service on port 10700 for HA voice pipeline
- Update setup.sh with cross-platform sed compatibility (macOS/Linux)
- Add version field to Kokoro TTS voice info
- Update launchd service loader to use Wyoming Satellite
## Home Assistant Integration (P4)
- Add custom conversation agent component (openclaw_conversation)
- Fix: Use IntentResponse instead of plain strings (HA API requirement)
- Support both HTTP API and CLI fallback modes
- Config flow for easy HA UI setup
- Add OpenClaw bridge scripts (Python + Bash)
- Add ha-ctl utility for HA entity control
- Fix: Use context manager for token file reading
- Add HA configuration examples and documentation
## Infrastructure
- Add mem0 backup automation (launchd + script)
- Add n8n workflow templates (morning briefing, notification router)
- Add VS Code workspace configuration
- Reorganize model files into categorized folders:
- lmstudio-community/
- mlx-community/
- bartowski/
- mradermacher/
## Documentation
- Update PROJECT_PLAN.md with Wyoming Satellite architecture
- Update TODO.md with completed Wyoming integration tasks
- Add OPENCLAW_INTEGRATION.md for HA setup guide
## Testing
- Verified Wyoming services running (STT:10300, TTS:10301, Satellite:10700)
- Verified OpenClaw CLI accessibility
- Confirmed cross-platform compatibility fixes
2026-03-08 02:06:37 +00:00
Aodhan Collins
c4f3dbed77
Phase 4: OpenClaw agent setup + expanded model catalog
...
- Add OpenClaw launchd plist (gateway on port 8080)
- Update Llama-3.3-70B Modelfile: fix FROM path, add tool-calling TEMPLATE,
set num_ctx 32768 (fits 70B in 64GB with safe headroom)
- Update Codestral-22B and Qwen3-32B Modelfiles
- Add Modelfiles for all models in ~/Models/LLM and ~/Models/MLX:
EVA-LLaMA-3.33-70B, Midnight-Miqu-70B, QwQ-32B, Qwen3.5-35B,
Qwen3-Coder-30B, Qwen3-Coder-Next, Qwen3-VL-30B, GLM-4.6V-Flash,
DeepSeek-R1-8B, gemma-3-27b, and MLX variants
- Add import-local-models.sh helper script
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-06 00:03:06 +00:00
Aodhan Collins
c31724c92b
Complete P2 (LLM) and P3 (voice pipeline) implementation
...
P2 — homeai-llm:
- Fix ollama launchd plist path for Apple Silicon (/opt/homebrew/bin/ollama)
- Add Modelfiles for local GGUF models: llama3.3:70b, qwen3:32b, codestral:22b
(registered via `ollama create` — no re-download needed)
P3 — homeai-voice:
- Wyoming STT: wyoming-faster-whisper, large-v3 model, port 10300
- Wyoming TTS: custom Kokoro ONNX server (wyoming_kokoro_server.py), port 10301
Voice af_heart; models at ~/models/kokoro/
- Wake word: openWakeWord daemon (hey_jarvis), notifies OpenClaw at /wake
- launchd plists for all three services + load-all-launchd.sh helper
- Smoke test: wyoming/test-pipeline.sh — 3/3 passing
HA Wyoming integration pending manual UI config (STT 10.0.0.200:10300,
TTS 10.0.0.200:10301).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-04 23:28:22 +00:00
