makecindy
Featured
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.
CutMind
CutMind is an intelligent diagnostic agent platform for industrial machining that combines LSTM tool wear prediction, CNN surface roughness assessment, RAG knowledge retrieval, industrial vision, and universal sensor diagnostics through a LangGraph workflow with natural language interaction.
Stars
6
7-day growth
No data
Forks
0
Open issues
0
License
No data
Last updated
2026-07-30
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It unifies multiple specialized AI models (LSTM, CNN, ShuffleNet, RAG) into a single conversational agent using LangGraph, enabling operators to diagnose tool wear and surface quality with natural language queries and file uploads.
Who it is for
- Industrial manufacturing engineers and technicians
- CNC machine operators and maintenance personnel
- Researchers in smart manufacturing and predictive maintenance
- Developers building domain-specific AI agent systems
Use cases
- Analyze sensor data to predict tool wear (VB) and surface roughness (Ra) in real time
- Upload workpiece photos for visual surface quality assessment via ShuffleNet
- Query industrial machining standards and knowledge base through RAG retrieval
- Compare wear trends across multiple machine tasks (e.g., CNC-001 vs CNC-002)
Strengths
- Combines multiple deep learning models (LSTM, 1D-CNN, ShuffleNet) under a single LangGraph agent for comprehensive diagnostics
- Supports natural language interaction via Ollama (qwen3:8b) without requiring coding
- Provides persistent conversation memory per task number (CNC-001 etc.) for traceable history
- Includes RAG knowledge retrieval from PDF documents to augment diagnosis with standards
Considerations
- Requires downloading a ~4.7GB Ollama model and separate datasets (NASA milling, machine data) before first use
- The RAG knowledge base is built automatically on first run but depends on users placing PDFs in the paper/ directory
- The repository mentions a subdirectory Earth-Agent-main that is not included, which may cause confusion
- Memory usage is recommended at 16GB+ for model inference, limiting deployment on low‑resource machines
README quick start
安装步骤
Description
工业加工智能 Agent 决策系统。基于 LangGraph 搭建，集成 LSTM 刀具磨损预测、CNN 表面粗糙度评估、RAG 知识库检索与工业视觉分析。
Related repositories
Similar projects matched by category, topics, and programming language.
uzairansaruzi
Featured
hermex
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.
hahhforest
Featured
pi-textbook
A hands-on course that walks through building a Pi-style coding agent from scratch across 15 checkpoints, starting from an offline agent trajectory.