经 AI Skill Hub 精选评估,阿耳忒弥斯 获评「强烈推荐」。这款AI工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
阿耳忒弥斯 是一款基于 Python 开发的开源工具,专注于 ai-girlfriend、desktop-pet、image-generation 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
阿耳忒弥斯 是一款基于 Python 开发的开源工具,专注于 ai-girlfriend、desktop-pet、image-generation 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:pip 安装(推荐)
pip install artemis
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install artemis
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/momori777/Artemis
cd Artemis
pip install -e .
# 验证安装
python -c "import artemis; print('安装成功')"
# 命令行使用
artemis --help
# 基本用法
artemis input_file -o output_file
# Python 代码中调用
import artemis
# 示例
result = artemis.process("input")
print(result)
# artemis 配置文件示例(config.yml) app: name: "artemis" debug: false log_level: "INFO" # 运行时指定配置文件 artemis --config config.yml # 或通过环境变量配置 export ARTEMIS_API_KEY="your-key" export ARTEMIS_OUTPUT_DIR="./output"
Fourth girlfriend voting in progress - please vote on Issues.
Baidu Netdisk: https://pan.baidu.com/s/1sLeSyVp76yzWcR3Q4pX0kA?pwd=0721 You don’t actually need Baidu Netdisk - HuggingFace mirrors work fine in China. Use it only if you really don’t want to configure hf-mirror.
⚠️ Default scripts are for NVIDIA GPUs. AMD GPU users: see the AMD_GPU/ folder.
qq: 580322386
| Skill | Type | Llama Kill? | Mechanism |
|---|---|---|---|
| **Embedding** | Background process | ❌No | all-MiniLM-L6-v2 + BGE-small-zh-v1.5 dual models (CPU, port 9999) -OpenClaw memory search + mem0 bridge |
| **Live2D** | HTTP exec | ❌No | Direct HTTP calls to localhost:19200 bridge |
| **Web Chat** | Browser | ❌ No | Local daemon proxy to llama :8080, port 19270 frontend, real-time chat with full character/multi-session support |
| **Claude Code** | Terminal (MCP) | ❌ No | Parallel agent runtime via .claude/artemis_mcp_server.py, uses llama :8080 directly |
| **TTS** | sessions_spawn | 🔶 VRAM-tiered | ≥12GB: no kill; 8GB: stop llama →GPT-SoVITS →restart llama |
| **ComfyUI** | sessions_spawn | 🔶 VRAM-tiered | ≥12GB: no kill; 8GB: stop llama →image gen →restart llama |
| **ASR** | sessions_spawn | ❌No | Faster-Whisper small (~1.5GB VRAM, coexists with llama) |
| **Sakura** | Shared llama-client | ❌No | Detects llama down →waits →auto-resumes |
| **Artemis Studio** | Desktop console | ❌No | TTS/ComfyUI visual workshop, standalone - works regardless of llama status |
memory/role_play/<character>/; agent restores context on role switchmemory/role_play/_mem0_auto.md every 30 min, making vector memories searchable by OpenClaw's native memory_searchuser_id scoping in Qdrant; 4 independent memory spaces (sakura / natsume / enola / atori)skills/character_importer/, import →agent auto-switches rolememory/role_play/<character>/, agent restores conversation context on role switch⚠️ First step: Runquick_setup.ps1to configure paths and language. This wizard will: 1. Let you choose the default Agent language (Chinese / Japanese / English) — copies the correspondingAGENTS_*.mdtoDEFAULT_AGENT.md2. Auto-detect your installed tools (ComfyUI, GPT-SoVITS, llama.cpp, embedding models) 3. Prompt you for any paths it can't find 4. Generateconfig.yamlwith all paths, ready fordownload-models.ps1After quick_setup completes, proceed with download-models.ps1 → setup-llama.ps1 → start.ps1.> powershell -ExecutionPolicy Bypass -File quick_setup.ps1 >
| Component | Version / Source | Purpose |
|---|---|---|
| [OpenClaw](https://docs.openclaw.ai) | latest | AI Agent Gateway |
| [Claude Code](https://github.com/anthropics/claude-code) | latest | Terminal-based AI agent (optional, MCP integration) |
| QQ Bot | OpenClaw qqbot channel | QQ message relay |
| Telegram Bot | OpenClaw telegram channel | Telegram message relay |
| [llama.cpp](https://github.com/ggml-org/llama.cpp) | b9222 | Local LLM inference server |
| [GPT-SoVITS v2](https://github.com/RVC-Boss/GPT-SoVITS) | v2pro-20250604 | TTS voice synthesis |
| [ComfyUI](https://github.com/comfyanonymous/ComfyUI) | aki-v3 | Image generation engine |
| [Sakura Desktop Pet](https://github.com/Rvosy/Sakura) | v0.9.6-dev | Desktop companion GUI |
| [pixi-live2d-display](https://github.com/guansss/pixi-live2d-display) | v0.5.0 (bundled) | Live2D WebGL renderer |
| Live2D Cubism Core | 4.x (bundled: live2d/live2dcubismcore.min.js) | Live2D physics/animation |
✨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 | | headroom | Bundled (skills/headroom/) | SmartCrusher context compression + ContentRouter + CCR | | Python | 3.12+ | Runtime (Sakura + TTS + ComfyUI) |
huggingface-cli login
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
Auto-detects GPU, VRAM, CPU cores, RAM and generates optimized launch configs.
Windows:
powershell -File setup-llama.ps1
Linux / macOS:
bash setup-llama.sh
quick_setup.ps1 -interactive wizard that generates config.yaml with your local pathsconfig.example.yaml →config.yaml and edit manuallymodels.yaml, then update config.yaml pathsAll 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.
powershell -File quick_setup.ps1
Interactive wizard -enter your local paths once, all scripts are updated automatically.
```powershell
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.
.\claude-code.ps1
| Feature | Artemis Task Board | AgentRQ (self-hosted) |
|---|---|---|
| Runtime | 1 Python script + SQLite | Go+Vue+Docker+Google OAuth |
| MCP tools | 6 task + 9 Artemis (15 total) | Same set (8 tools) |
| Setup | Zero config | Docker + .env + OAuth |
高品质AI工具,功能丰富
该工具使用 NOASSERTION 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
AI Skill Hub 点评:阿耳忒弥斯 的核心功能完整,质量优秀。对于AI 技术爱好者来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | Artemis |
| 原始描述 | 开源AI工具:破限本地AI女友后宫,openclaw/claude code+画图语音向量数据库+live2D+桌宠+酒馆角色卡导入+前端,QQ+Telegram双通道,8G。⭐146 · Python |
| Topics | ai-girlfrienddesktop-petimage-generation |
| GitHub | https://github.com/momori777/Artemis |
| License | NOASSERTION |
| 语言 | Python |
收录时间:2026-06-27 · 更新时间:2026-06-27 · License:NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。