阿耳忒弥斯

📌 Prerequisites

⚠️ First step: Run quick_setup.ps1 to configure paths and language. This wizard will: 1. Let you choose the default Agent language (Chinese / Japanese / English) - copies the corresponding AGENTS_*.md to DEFAULT_AGENT.md 2. Auto-detect your installed tools (ComfyUI, GPT-SoVITS, llama.cpp, embedding models) 3. Prompt you for any paths it can't find 4. Generate config.yaml with all paths, ready for download-models.ps1

> powershell -ExecutionPolicy Bypass -File quick_setup.ps1
> 

After quick_setup completes, proceed with download-models.ps1 → setup-llama.ps1 → start.ps1.

Prerequisites: npm install -g @anthropic-ai/claude-code

Environment Dependencies

✨TTS, ComfyUI, and Live2D are fully self-contained. No external downloads at runtime -all model weights (skills/sovits/, skills/comfyui_core/), Python scripts, JS libraries (live2d/pixi.min.js, live2d/plid-v5-bundle.js), and Cubism Core 4 (live2d/live2dcubismcore.min.js) are bundled locally. 🧠 Headroom token-saving -skills/headroom/ (SmartCrusher + ContentRouter + CCR). Compress large tool outputs in dev scenarios before they hit the context window. See AGENTS.md for API usage. | headroom | Bundled (skills/headroom/) | SmartCrusher context compression + ContentRouter + CCR | | Python | 3.12+ | Runtime (Sakura + TTS + ComfyUI + Headroom) |

Install huggingface-cli: pip install huggingface_hub

huggingface-cli login

0. Setup OpenClaw

Install OpenClaw Gateway and deploy the AI Girlfriend workspace:

Windows:

powershell -File setup-openclaw.ps1

Linux / macOS:

bash setup-openclaw.sh

This script installs Node.js, OpenClaw Gateway, deploys workspace files, installs daemon, and applies config patch.

Flags: --skip-node, --skip-deploy, --skip-daemon, --no-onboard

2. Setup llama.cpp

Auto-detects GPU, VRAM, CPU cores, RAM and generates optimized launch configs.

Windows:

powershell -File setup-llama.ps1

Linux / macOS:

bash setup-llama.sh

API Key (optional, recommended):

From this version, llama-server enables API key authentication by default (for security and extensibility). Configure in config.yaml:

llama_api_key: "123456"   # change to your own key; leave empty to skip --api-key

• After setting, the llama-server inference endpoints (/v1/chat/completions, etc.) require requests with Authorization: Bearer <key> or api_key:<key>.
• /health remains unauthenticated (health checks unaffected).
• All clients (headroom proxy / sakura / shiki_daemon forwarding) will automatically read llama_api_key and include the key, no additional config needed.
• When connecting to CCR, the CCR provider config also needs the upstream API key set to the same value.

Quick Start

🎬 Demo

Local Configuration

1. Run quick_setup.ps1 -interactive wizard that generates config.yaml with your local paths
2. (Alternative) Copy config.example.yaml →config.yaml and edit manually
3. Place downloaded model files according to models.yaml, then update config.yaml paths

All Python/PS scripts read paths from config.yaml -no hardcoded paths to edit.

⚠️ Disclaimer: All models are community open-source. This project only provides mirror distribution, non-profit. Copyright belongs to original authors.

Equivalent manual command (what the reference config generates)

Start-Process -FilePath $exe -ArgumentList @( "-m", "D:\model\Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-MTP-Q4_K_S.gguf", "-c", "100000", "--flash-attn", "on", "-ctk", "q4_0", "-ctv", "q4_0", "-ngl", "14", "--batch-size", "2048", "--ubatch-size", "1024", "--jinja", "--reasoning-preserve", "--chat-template-file", "D:\AI_Girlfriend\chat_template.jinja", "--cache-ram", "2000", "--parallel", "1", "--kv-unified", "--no-mmap", "--no-warmup", "--spec-type", "draft-mtp", "--spec-draft-n-max", "3", "--spec-draft-p-min", "0.88", "--spec-draft-ngl", "99" ) ```

Reference hardware: i9-14900HX + RTX 5070 Laptop (8 GB) + 64 GB RAM. The model weights are split via a partial offload -ngl 14 (first 14 layers on GPU, rest in RAM with --no-mmap); KV cache uses --cache-ram 2000; the MTP draft context is offloaded fully to the GPU (--spec-draft-ngl 99) so speculative decoding stays fast on an 8 GB card. Q4_K_S quantization keeps the model at ~15.8 GB — the sweet spot for dense 27B on consumer hardware. rea not specified — defaults to medium reasoning depth via the chat template. Full flag-by-flag breakdown, hardware notes, and live-log metrics are in the "Qwen3.8-27B Dense (primary tooling model)" section above.

3. Configure Paths

powershell -File quick_setup.ps1

Interactive wizard - enter your local paths once, all scripts are updated automatically.

5. Windows Task Scheduler (optional)

```powershell

Or download individual components:

huggingface-cli download TAOTAO777/ai-girlfriend-natsume llm/ --local-dir ./models huggingface-cli download TAOTAO777/ai-girlfriend-natsume comfyui-checkpoints/ --local-dir ./checkpoints huggingface-cli download TAOTAO777/ai-girlfriend-natsume gpt-sovits-weights/ --local-dir ./gpt-sovits-weights huggingface-cli download TAOTAO777/ai-girlfriend-natsume live2d-model/ --local-dir ./live2d-model ```

🇨🇳 Users in China: use hf-mirror.com - no VPN needed: set HF_ENDPOINT=https://hf-mirror.com then run hf download as usual.

Full AgentRQ workflow (Task Board + Claude Code)

.\claude-code.ps1

Headroom + Mem0 Pipeline (port 19251)

OpenClaw Gateway (18789)
  ├─ <provider>/<model-id>           → Direct to original backend (skips headroom)
  ├─ local-llama/llama-local          → 19251 → llama-server:8080
  └─ local-llama/<model-id>           → 19251 → original backend (via headroom+mem0)
         │
         ▼
  headroom proxy (19251)
    ├─ [1] mem0 character memory injection (Qdrant vector search)
    ├─ [2] SmartCrusher 5-dim compressed conversation history
    └─ [3] Route to real backend
         ├─ llama-local → llama-server:8080
         └─ Cloud models    → sidecar finds real baseUrl

Add-only, no-change principle: start.ps1 auto-scans ~/.openclaw/openclaw.json on startup, adds local-llama provider (copies existing cloud model), original providers left as-is. Original baseUrl stored in ~/.openclaw/headroom_routes.json sidecar file. Zero-config after clone.

Artemis Task Board vs AgentRQ