labring/tentix

TenTix (10x Efficiency) - An AI native customer service platform with 10x accelerated resolution. Support MCP extension, and AI knowlage base system.

What it solves

Tentix is an AI-native customer service platform designed to accelerate ticket resolution. It reduces the need for human intervention and improves response times by automating the initial handling of customer inquiries using a knowledge-driven AI agent.

How it works

Tentix uses a RAG (Retrieval-Augmented Generation) architecture powered by a LangGraph AI Agent. It builds a unified vector knowledge base using PostgreSQL and pgvector, sourcing data from three priority levels: starred conversations, historical tickets, and general documentation. When a user sends a message, the system refines the query, retrieves relevant knowledge based on weighted priorities, and generates a response. It also supports human handoff and modular integration nodes for extended functionality.

Who it’s for

It is built for businesses and support teams that want to automate their customer service ticketing systems while maintaining the ability to hand off complex issues to human staff.

Highlights

  • Weighted Knowledge Retrieval: Prioritizes information from starred conversations and high-quality historical tickets over general docs.
  • Configurable AI Workflows: Supports RAG, human handoff, and MCP-style integration nodes.
  • Admin KB Management: Tools to browse, edit, and rebuild indexes for the knowledge base.
  • Multi-channel Support: Includes built-in support for Feishu notifications and a modular design for other IM or form integrations.
  • Flexible Backend: Compatible with PostgreSQL + pgvector or external services like FastGPT.

Related

  • Project
    Bytedesk/bytedesk

    An AI-powered omnichannel customer service platform that integrates chat, tickets, and call centers with AI agents and RAG for automated support.

  • Project
    xerrors/Yuxi

    A self-deployable, multi-tenant knowledge agent platform that integrates RAG, knowledge graphs, and multi-agent orchestration for secure team collaboration.

  • Project
    langflow-ai/openrag

    An intelligent agent-powered document search platform that enables users to upload, process, and query documents through a chat interface using RAG.

  • Project
    liangdabiao/langgraph_multi-agent-rag-customer-support

    A multi-agent RAG customer support system built with LangGraph and LangChain that features security guardrails and a human-in-the-loop approval process for sensitive operations.

  • Project
    datavane/tis

    An AI-native data integration platform that uses LLMs and GraphRAG to enable natural language creation of data pipelines and SQL-free data analysis.