能力标签
阿耳忒弥斯
🛠
AI工具

阿耳忒弥斯

基于 Python · 开源免费,本地部署,数据完全自主可控
英文名:Artemis
⭐ 146 Stars 🍴 8 Forks 💻 Python 📄 NOASSERTION 🏷 AI 8.0分
8.0AI 综合评分
ai-girlfrienddesktop-petimage-generation
✦ AI Skill Hub 推荐

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。

📚 深度解析

阿耳忒弥斯 是一款基于 Python 的开源工具,在 GitHub 上收获 0k+ Star,是ai-girlfriend、desktop-pet、image-generation领域中的优质开源项目。开源工具的最大优势在于代码完全透明,你可以审计每一行代码的安全性,也可以根据自身需求进行二次开发和定制。

**为什么要使用开源工具而非商业 SaaS?**
对于个人开发者和有隐私需求的用户,本地部署的开源工具意味着数据不离本机,不受第三方服务商的数据政策约束。同时,开源工具通常没有使用次数限制和月度费用,一次安装即可长期使用,对于高频使用场景的总拥有成本(TCO)远低于订阅制商业工具。

**安装与环境准备**
阿耳忒弥斯 依赖 Python 运行环境。建议通过 pyenv(Python)或 nvm(Node.js)管理 Python 版本,避免全局环境污染。对于新手用户,推荐先创建虚拟环境(python -m venv venv && source venv/bin/activate),再安装依赖,这样即使出现问题也可以随时删除虚拟环境重新开始,不影响系统稳定性。

**社区与维护**
GitHub Issue 和 Discussion 是获取帮助的最快渠道。在提问前建议先检查 Closed Issues(已关闭的问题),大多数常见问题都已有解答。遇到 Bug 时,提供 pip list 的输出、完整错误堆栈和最小可复现示例,能显著提高开发者响应速度。AI Skill Hub 将持续追踪 阿耳忒弥斯 的版本更新,及时通知重要功能变化。

📋 工具概览

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。

GitHub Stars
⭐ 146
开发语言
Python
支持平台
Windows / macOS / Linux
维护状态
轻量级项目,按需更新
开源协议
NOASSERTION
AI 综合评分
8.0 分
工具类型
AI工具
Forks
8

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理,如需查看完整原始文档请访问底部「原始来源」。

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。

📌 核心特色
  • 开源免费,支持本地部署,数据完全自主可控
  • 活跃的 GitHub 开源社区,持续迭代更新
  • 提供详细文档和使用示例,新手友好
  • 支持自定义配置,灵活适配不同使用环境
  • 可作为基础组件集成进现有技术栈或进行二次开发
🎯 主要使用场景
  • 本地部署运行,保护数据隐私,满足合规要求
  • 自定义集成到现有系统,扩展技术栈能力
  • 作为开源基础组件进行商业化二次开发
以下安装命令基于项目开发语言和类型自动生成,实际以官方 README 为准。
安装命令
# 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')"
📋 安装步骤说明
  1. 访问 GitHub 仓库页面
  2. 按照 README 文档完成依赖安装
  3. 根据系统环境完成初始化配置
  4. 参考官方示例或文档开始使用
  5. 遇到问题可在 GitHub Issues 中查找解答
以下用法示例由 AI Skill Hub 整理,涵盖最常见的使用场景。
常用命令 / 代码示例
# 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)
以下配置示例基于典型使用场景生成,具体参数请参照官方文档调整。
配置示例
# 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"
📑 README 深度解析 真实文档 完整度 80/100 查看 GitHub 原文 →
以下内容由系统直接从 GitHub README 解析整理,保留代码块、表格与列表结构。

简介

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

Skills Overview

SkillTypeLlama Kill?Mechanism
**Embedding**Background process❌Noall-MiniLM-L6-v2 + BGE-small-zh-v1.5 dual models (CPU, port 9999) -OpenClaw memory search + mem0 bridge
**Live2D**HTTP exec❌NoDirect HTTP calls to localhost:19200 bridge
**Web Chat**Browser❌ NoLocal daemon proxy to llama :8080, port 19270 frontend, real-time chat with full character/multi-session support
**Claude Code**Terminal (MCP)❌ NoParallel 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❌NoFaster-Whisper small (~1.5GB VRAM, coexists with llama)
**Sakura**Shared llama-client❌NoDetects llama down →waits →auto-resumes
**Artemis Studio**Desktop console❌NoTTS/ComfyUI visual workshop, standalone - works regardless of llama status

Features

  • 🔄 Multi-Character Hot-Swap - One-click switch between AI girlfriends (Natsume ⇄ ATRI ⇄ Sakura); SOUL/IDENTITY/TTS weights/Live2D model all switch automatically, memories isolated per character
  • 🃏 SillyTavern Character Card Import - Auto-detect and import PNG/JSON character cards; agent auto-switches persona on import
  • 💬 Chat Log Import - Import SillyTavern JSONL conversation logs into memory/role_play/<character>/; agent restores context on role switch
  • 🎤 TTS Voice Synthesis -Local GPT-SoVITS inference, Japanese voice (emotion-matched per dialogue), 3 character voice models (Natsume / ATRI / Sakura)
  • 🎤 ASR Speech Recognition -Local Faster-Whisper small model (~1.5GB VRAM), coexists with llama; 99-language support
  • 🎨 AI Image Generation -Local ComfyUI inference, SDXL/Illustrious models, 3 character prompt templates
  • 🖥️Sakura Desktop Pet -PySide6 desktop companion with proactive care, screen observation & local LLM awareness; supports 3 characters
  • 🎭 Live2D Character Model -Real-time Live2D rendering with emotion-driven expressions & speech bubbles (Natsume / ATRI L2D; Sakura portrait mode)
  • 🧠 Smart VRAM Tiering - Auto-detects GPU VRAM and picks the right strategy: ≥12GB keeps everything online (llama + skills); 8GB hot-swaps llama for GPU-heavy tasks; <8GB safe mode. Zero manual config
  • 🎛️ Artemis Studio Console - Visual TTS + ComfyUI workshop, DIY voice & images anytime regardless of llama status - a true offline creative suite
  • 💾 Roleplay Memory -Daily conversation summaries per character in memory/role_play/
  • 🧠 Long-term Memory System -Powered by headroom (SmartCrusher + CCR) and mem0 (Qdrant vector database):
  • Chinese Embedding Boost - Added BGE-small-zh-v1.5 alongside all-MiniLM-L6-v2 for more accurate CN/JP/EN hybrid memory retrieval
  • SmartCrusher Context Trimming -Hard-caps chat history at 24 messages / 40K characters per LLM request
  • CCR (Curate-Consolidate-Retrieve) -Background worker extracts durable facts every 8 turns, writes to mem0 Qdrant
  • Vector + BM25 Hybrid Search -Semantic similarity + keyword matching via Qdrant + dual embedding models
  • Auto-Sync Bridge -Cron job syncs Qdrant →_mem0_auto.md every 30 min, making vector memories searchable by OpenClaw's native memory_search
  • Per-Character Isolation -user_id scoping in Qdrant; 4 independent memory spaces (sakura / natsume / enola / atori)
  • Recall Priority -Vector long-term memories > handwritten daily notes > SOUL base persona
  • 🔄 Multi-Character Hot-Swap -Switch between AI girlfriends (Natsume ↔ATRI ↔Sakura) with one command; SOUL/IDENTITY/TTS weights/Live2D model all switch automatically, memories isolated per character
  • 🃏 Character Card Import -Auto-detect SillyTavern character cards via skills/character_importer/, import →agent auto-switches role
  • 💬 Chat Import -Import SillyTavern JSONL chat logs into memory/role_play/<character>/, agent restores conversation context on role switch

📌 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.ps1setup-llama.ps1start.ps1.

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

Prerequisites

ComponentVersion / SourcePurpose
[OpenClaw](https://docs.openclaw.ai)latestAI Agent Gateway
[Claude Code](https://github.com/anthropics/claude-code)latestTerminal-based AI agent (optional, MCP integration)
QQ BotOpenClaw qqbot channelQQ message relay
Telegram BotOpenClaw telegram channelTelegram message relay
[llama.cpp](https://github.com/ggml-org/llama.cpp)b9222Local LLM inference server
[GPT-SoVITS v2](https://github.com/RVC-Boss/GPT-SoVITS)v2pro-20250604TTS voice synthesis
[ComfyUI](https://github.com/comfyanonymous/ComfyUI)aki-v3Image generation engine
[Sakura Desktop Pet](https://github.com/Rvosy/Sakura)v0.9.6-devDesktop companion GUI
[pixi-live2d-display](https://github.com/guansss/pixi-live2d-display)v0.5.0 (bundled)Live2D WebGL renderer
Live2D Cubism Core4.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) |

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

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.yamlconfig.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.

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

Artemis Task Board vs AgentRQ

FeatureArtemis Task BoardAgentRQ (self-hosted)
Runtime1 Python script + SQLiteGo+Vue+Docker+Google OAuth
MCP tools6 task + 9 Artemis (15 total)Same set (8 tools)
SetupZero configDocker + .env + OAuth
🎯 aiskill88 AI 点评 A 级 2026-06-27

高品质AI工具,功能丰富

⚡ 核心功能

👥 适合人群

AI 技术爱好者研究人员和学生开发者和工程师技术创业者

🎯 使用场景

  • 本地部署运行,保护数据隐私,满足合规要求
  • 自定义集成到现有系统,扩展技术栈能力
  • 作为开源基础组件进行商业化二次开发

⚖️ 优点与不足

✅ 优点
  • +完全开源免费,无授权费用
  • +本地部署,数据完全自主可控
  • +开发者社区支持,遇问题可查可问
⚠️ 不足
  • 安装和初始配置可能需要一定技术基础
  • 功能完整性通常不如成熟商业产品
  • 技术支持主要依赖开源社区,响应速度不稳定
⚠️ 使用须知

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。

📄 License 说明

📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。

🔗 相关工具推荐

🧩 你可能还需要
基于当前 Skill 的能力图谱,自动补全的工具组合

❓ 常见问题 FAQ

通过live2D和酒馆角色卡导入功能
💡 AI Skill Hub 点评

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。

📚 深入学习 阿耳忒弥斯
查看分步骤安装教程和完整使用指南,快速上手这款工具
🌐 原始信息
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
🔗 原始来源
🐙 GitHub 仓库  https://github.com/momori777/Artemis

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。

📺 订阅 AI Skill Hub Daily Telegram 频道
每天 8 条精选 AI Skill、MCP、Agent 与自动化工具推送
加入频道 →