Character schema v2: background, dialogue_style, appearance, skills, gaze_presets
with automatic v1→v2 migration. LLM-assisted character creation via Character MCP
server. Two-tier memory system (personal per-character + general shared) with
budget-based injection into LLM system prompt. Per-character TTS voice routing via
state file — Wyoming TTS server reads active config to route between Kokoro (local)
and ElevenLabs (cloud PCM 24kHz). Dashboard: memories page, conversation history,
character profile on cards, auto-TTS engine selection from character config.
Also includes VTube Studio expression bridge and ComfyUI API guide.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- 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>
- Root setup.sh orchestrator with per-phase dispatch (./setup.sh p1..p8 | all | status)
- Makefile convenience targets (make infra, make llm, make status, etc.)
- scripts/common.sh: shared bash library for OS detection, Docker helpers,
service management (launchd/systemd), package install, env management
- .env.example + .gitignore: shared config template and secret exclusions
P1 (homeai-infra): full implementation
- docker-compose.yml: Uptime Kuma, code-server, n8n
- Note: Home Assistant, Portainer, Gitea are pre-existing instances
- setup.sh: Docker install, homeai network, container health checks
P2 (homeai-llm): full implementation
- Ollama native install with CUDA/ROCm/Metal auto-detection
- launchd plist (macOS) + systemd service (Linux) for auto-start
- scripts/pull-models.sh: idempotent model puller from manifest
- scripts/benchmark.sh: tokens/sec measurement per model
- Open WebUI on port 3030 (avoids Gitea :3000 conflict)
P3-P8: working stubs with prerequisite checks and TODO sections
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
