cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.
EquipDoc-Agent is an auditable, degradable AI agent for electromechanical equipment maintenance that combines deterministic safety policies, human-in-the-loop approval via LangGraph, and optional RAG to generate evidence-based diagnostic reports for bearing vibration signals.
12
No data
0
0
NOASSERTION
2026-07-29
It demonstrates a principled engineering approach to agent safety by enforcing explicit human approval before tool execution, providing clear degradation modes (Demo/Full), and delivering reproducible evaluation baselines with measurable regression thresholds.
面向机电设备运维场景的可审核、可降级 Agent。项目将确定性安全策略、LangGraph 人工审核、轴承振动信号诊断工具、可选 RAG 和证据化报告组织为一个可复现的公开工程作品。
当前公开版本默认运行在无模型 Demo 模式:可以完整演示 Agent 工作流,但故障类型是明确标注的固定案例回放,不能作为真实设备诊断结果。Full 模式需要单独配置 Qwen 服务、CNN 权重和可选向量库。
| 项目维度 | 当前实现 |
|---|---|
| 目标场景 | 轴承振动信号辅助分析与运维报告生成 |
| Agent 编排 | LangGraph 状态图、条件路由、可恢复中断 |
| 人机协同 | 诊断工具执行前必须 Approve/Reject |
| 工具能力 | .npy 信号校验、CNN 诊断接口、知识检索、报告生成 |
| 安全边界 | 上传沙箱、大小与数值检查、路径白名单、显式降级 |
| 运行方式 | 本地 Gradio、Docker、AutoDL Full 模式 |
| 当前证据 | 单元测试、Smoke Test、历史实验文件和限制说明 |
通用大模型无法直接分析振动时序信号,也容易在设备信息不足时生成缺少依据的维修建议。本项目把自然语言交互与专用诊断工具分离,并在高影响工具调用前加入人工审核:
flowchart LR
A[上传振动信号] --> B[安全校验]
B --> C[策略判断任务边界]
C --> D{人工审核}
D -->|Approve| E[轴承诊断工具]
D -->|Reject| F[终止工具调用]
E --> G[检索故障机理与维护依据]
G --> H[生成带证据与边界的报告]
项目不控制真实设备,不替代工程师作出高风险维修决策,也不根据单段信号预测精确剩余寿命。
.npy 一维信号;pyproject.toml、环境变量、Docker、健康检查、Smoke Test 和 CI。诊断工具调用前,系统会暂停工作流并等待人工审核。审核界面只展示工具名称和经过脱敏的文件名,不暴露服务器内部路径。
审批通过后,系统输出带 Demo 标识、检索证据、处理建议和适用边界的报告:
Windows PowerShell:
python -m venv .venv
.\.venv\Scripts\Activate.ps1
python -m pip install --upgrade pip
pip install -e ".[demo]"
Copy-Item .env.example .env
Linux / AutoDL:
python -m venv .venv
source .venv/bin/activate
python -m pip install --upgrade pip
pip install -e ".[demo]"
cp .env.example .env
python -m equipdoc_agent.health --strict
python scripts/demo_smoke.py
python -m unittest discover -s tests -v
Demo 模式下,bearing_model、bearing_norm 和 rag_vector_db 可以显示为不存在,因为它们不是必需项。
python app_gradio.py
打开终端显示的本地地址,默认是:
http://127.0.0.1:7860
若 7860 已被占用,应用会自动尝试 7861、7862 等端口。
Approve 继续生成报告,或点击 Reject 验证拒绝分支;Auditable AI agent for electromechanical maintenance with LangGraph, RAG, fault diagnosis and human-in-the-loop review.
Similar projects matched by category, topics, and programming language.
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.

Hermex is a native SwiftUI iPhone app that lets you control a self-hosted Hermes AI agent directly from your phone, with no subscriptions, tracking, or third-party relay.
A hands-on course that walks through building a Pi-style coding agent from scratch across 15 checkpoints, starting from an offline agent trajectory.