LangChat/langchat

LangChat 是Java&LangChain4j生态的开源 AI Agent 应用平台，支持多模型、Agent、知识库 RAG、Skills、MCP 与智能问数。

What it solves

LangChat is a modular, extensible open-source AI Agent application platform. It solves the complexity of building and deploying AI applications by integrating model access, Agent construction, RAG-based knowledge bases, skill extensions, and data analysis into a single Java and Vue-based ecosystem.

How it works

The platform uses a modular monolith architecture (divided into auth, aigc, core, datasource, and server modules) to balance deployment simplicity with future scalability. It provides a unified AI runtime that decouples business code from specific model SDKs, allowing developers to assemble Agents using models, knowledge bases, and tools. It supports multiple LLM providers (OpenAI, Azure, Anthropic, Gemini, DeepSeek, etc.) and integrates with vector stores like Pgvector and Milvus.

Who it’s for

It is designed for developers and teams who need to perform technical validation, secondary development, or build internal AI tools and agents for their organizations.

Highlights

  • Unified AI Runtime: Decouples business logic from model SDKs for easier model switching.
  • Comprehensive Tooling: Integrates RAG, MCP (Model Context Protocol) services, and custom skill registration.
  • Structured Data Analysis: Combines document-based retrieval with natural language querying of structured data sources (Text2SQL).
  • Open API Access: Provides both platform APIs and OpenAI-compatible Chat Completions interfaces.
  • Full Management UI: A complete Vue 3 interface for managing models, agents, knowledge bases, and user permissions (RBAC).

Related

  • Project
    Shy2593666979/AgentChat

    AgentChat is an open‑source, full‑stack conversational AI platform. It combines a Vue 3 front‑end with a FastAPI + LangChain back‑end to deliver LLM‑driven chat, multi‑agent collaboration, three‑tier memory (short‑term, summarised history, long‑term user prefs), RAG via vector stores, tool calling (including custom OpenAPI tools), and Model‑Context‑Protocol integration. Docker‑compose provides one‑click deployment; the project is MIT‑licensed.

  • Project
    JoshuaC215/agent-service-toolkit

    A comprehensive toolkit for building and deploying AI agents using LangGraph, FastAPI, and Streamlit, providing a complete template from agent logic to user interface.

  • Project
    langbot-app/LangBot

    Open-source platform that unifies LLMs (OpenAI, DeepSeek, local Ollama, etc.) into AI agents deployable across Slack, Discord, Telegram, WeChat, QQ, and more—with a web dashboard, plugin marketplace, and MCP/CLI tools so human or AI developers can manage every bot from one place.

  • Project
    cqzyys/lang-agent

    A visual configuration platform based on LangGraph that allows users to build complex AI agents using a drag-and-drop interface with customizable state variables for precise logic control.

  • Project
    moyangzhan/langchain4j-aideepin

    An AI application platform for building business assistants that integrates AI chat, RAG, visual workflow orchestration, and multimodal capabilities.