chengrouter/chengos

ChengOS is a visual AI data processing and agent workflow system. This directory contains deployment scripts, infrastructure configs, and runtime resources for production and development.

What it solves

ChengOS provides a unified platform to build, deploy, and run AI agents and complex automation workflows without needing to write extensive code. It bridges the gap between designing a workflow visually and deploying it across multiple channels like web apps, mobile interfaces, and terminal clients.

How it works

It uses a client-server architecture with a high-performance Rust-based DAG (Directed Acyclic Graph) engine for execution. Users design workflows on a React Flow canvas, which are then executed by the backend. The system integrates with LLMs, MCP (Model Context Protocol) servers, and a custom "Skill" system that allows importing capabilities from natural language or API docs. It also includes built-in support for RAG (Retrieval-Augmented Generation) and direct manipulation of local documents and spreadsheets.

Who it’s for

It is designed for developers and automation specialists who want to create sophisticated AI agents and data processing pipelines that can be accessed via various chat interfaces or a command-line interface.

Highlights

  • Visual Workflow Editor: A drag-and-drop canvas for building and testing AI agents and automation.
  • Native MCP Support: Ability to connect to MCP servers via Stdio, SSE, or HTTP for dynamic tool discovery.
  • Crendential Isolation: Secrets are stored in a secure backend vault and injected only at runtime, keeping them out of LLM prompts.
  • Multi-Channel Deployment: Publish agents to Web, PWA, WhatsApp, Telegram, Slack, and a dedicated terminal client.
  • Integrated RAG & Document Handling: Built-in nodes for chunking, indexing, and editing .docx and .xlsx files without third-party office suites.

Related

  • Project
    CGCL-codes/naturalcc

    A sequence modeling toolkit for code intelligence that enables training and evaluating models for tasks like code generation, summarization, and retrieval.

  • Project
    AdamPlatin123/Open-Deep-Research-workflow-on-Dify

    A Dify workflow that replicates Deep Research functionality to generate long-form, structured research reports using multi-source retrieval and multi-model collaboration.

  • Project
    fabriziosalmi/UglyFeed

    An LLM-powered application that retrieves, aggregates, and rewrites RSS feeds to create curated, high-quality content streams.

  • Project
    jiabaobei/memory-bridge

    A cross-device shared memory layer for AI agents that uses encrypted cloud drive synchronization to maintain a continuous semantic memory across different platforms and devices.