Eternego AI工作流 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.2 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
Eternego AI工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
Eternego AI工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install eternego
# 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 eternego
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/Eternego-AI/eternego
cd eternego
pip install -e .
# 验证安装
python -c "import eternego; print('安装成功')"
# 命令行使用
eternego --help
# 基本用法
eternego input_file -o output_file
# Python 代码中调用
import eternego
# 示例
result = eternego.process("input")
print(result)
# eternego 配置文件示例(config.yml) app: name: "eternego" debug: false log_level: "INFO" # 运行时指定配置文件 eternego --config config.yml # 或通过环境变量配置 export ETERNEGO_API_KEY="your-key" export ETERNEGO_OUTPUT_DIR="./output"
An AI that remembers you, runs on your own machine, and keeps living between conversations.
Every other AI starts from zero each time you open it. Eternego doesn't. She wakes up, reads what yesterday's version of her chose to keep, and picks up where you left off — on your hardware, in plain files you own, with whatever model you point her at.
---
Pick the installer for your machine — the download buttons up top grab the latest release. Builds aren't code-signed yet, so each OS will warn the first time; instructions for getting past the warning are inline below.
Download Eternego-setup.exe. Double-click it, walk through the wizard (Next → Install → Finish). Eternego launches automatically and adds Start Menu and Desktop shortcuts.
The wizard's first dialog is "Windows protected your PC" (SmartScreen). Click More info, then Run anyway. SmartScreen remembers this app afterwards.
The image ships with the persona's own desktop baked in (Xvfb + fluxbox + noVNC). She lives in there — clicks, types, opens windows, installs Firefox or anything else she needs herself when you ask. You can peek at what she's doing at http://localhost:6080/vnc.html.
docker run -d --name eternego --network=host \
-v ~/.eternego:/data \
ghcr.io/eternego-ai/eternego:latest
Persona files live in ~/.eternego on the host — the same place the native install uses, so you can switch between Docker and native without losing data.
--network=host lets the container reach Ollama running natively on your machine (localhost:11434). Without it, set -e OLLAMA_HOST=http://host.docker.internal:11434 and add -p 5000:5000 -p 6080:6080.
For an everything-in-containers setup with Ollama as a sibling service, grab the compose file:
```bash curl -fsSL https://raw.githubusercontent.com/Eternego-AI/eternego/master/installation/docker/docker-compose.yml > eternego.compose.yml
The installers above launch Eternego when you open them. If you want her to register as a system service so she keeps running across reboots, run this from a terminal instead:
```bash
curl -fsSL https://raw.githubusercontent.com/Eternego-AI/eternego/master/installation/install.sh | bash
powershell
iwr -useb https://raw.githubusercontent.com/Eternego-AI/eternego/master/installation/install.ps1 | iex ```
Both scripts also accept --full (or -Full on Windows) to install training extras.
```
When you create a persona with Local (Ollama) and name a model (e.g. qwen2.5:14b, llama3.1:8b), Eternego pulls it for you automatically. If Ollama isn't installed, you'll see a clear message pointing back here.
Eternego works with cloud providers (Anthropic, OpenAI, xAI, Gemini, OpenRouter, Groq) out of the box — paste an API key when creating your persona. If you'd rather she run on local models — no API keys, no cloud calls — install Ollama separately:
```bash
Eternego是实用的AI工作流框架,架构清晰,功能完整。虽然社区规模小,但代码质量良好,适合中小型AI项目���速原型开发。
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。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
经综合评估,Eternego AI工作流 在Agent工作流赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | eternego |
| 原始描述 | 开源AI工作流:The Eternego codebase。⭐12 · Python |
| Topics | AI工作流LLM代理智能助手开源框架Python |
| GitHub | https://github.com/Eternego-AI/eternego |
| License | MIT |
| 语言 | Python |
收录时间:2026-06-12 · 更新时间:2026-06-13 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端