Repolode
Submit
LangChat

LangChat/langchat

Open-source AI agent application platform built on Java, LangChain4j, Spring Boot and Vue 3, covering models, agents, RAG, Skills, MCP and text-to-SQL analysis.

View on GitHubWebsite
Stars
1,316
Forks
256
Open issues
2
Last commit
24 days ago

What is it?

LangChat is a modular AI agent application platform for building and running LLM-based apps on a Java and Vue stack. It connects multiple model providers such as OpenAI, Azure OpenAI, Anthropic, Gemini, DeepSeek, Qwen, Zhipu and Ollama through one configuration layer, and lets you assemble agents from a system prompt, knowledge bases, Skills and MCP services.

The knowledge base module handles document upload, parsing, chunking, indexing status and vector store configuration for retrieval-augmented generation, with Pgvector and Milvus listed as vector backends. A separate data analysis module connects to databases, reads their schema and answers natural-language questions with results and charts. The chat runtime supports SSE streaming and exposes an OpenAI-compatible Chat Completions endpoint.

The backend is organized as a Maven multi-module modular monolith (Java 17, Spring Boot 3.3, LangChain4j, MyBatis-Plus, Sa-Token), and the admin UI is built with Vue 3, TypeScript and Naive UI. It includes RBAC for users, roles and menus, and Docker Compose deployment scripts.

Key features

  • 01Unified management of multiple LLM providers, including OpenAI-compatible services and Ollama.
  • 02Agent builder with prompts, knowledge bases, Skills and MCP configuration plus debugging UI.
  • 03Knowledge base RAG with document parsing, chunking, indexing and Pgvector or Milvus storage.
  • 04OpenAI-compatible Chat Completions API with SSE streaming.
  • 05Natural-language data analysis that generates results and charts from connected data sources.
  • 06RBAC management for users, roles, menus and dynamic routes.

Use cases

  • Java teams building internal AI assistants on Spring Boot.
  • Adding document question answering over company knowledge bases.
  • Exposing agents through an OpenAI-compatible API to existing clients.
  • Letting business users query databases in natural language with charts.

Quick start

  1. 1

    Clone the repository (next branch)

    git clone -b next https://github.com/langchat/langchat.git
  2. 2

    Install frontend dependencies in langchat-ui

    pnpm install
  3. 3

    Copy the local config example and fill in database settings

    cp langchat-server/src/main/resources/application-local.example.yml langchat-server/src/main/resources/application-local.yml
  4. 4

    Start the project

    SPRING_PROFILES_ACTIVE=local ./langchat.sh

Things to know

  • Requires JDK 17+, Maven 3.9+, Node.js 22.22+, pnpm 10.32+ and MySQL 8+ before it runs.
  • The open-source edition has fewer features than the commercial LangChat Agentic edition.
  • Development happens on the next branch, which is the baseline for pull requests.

Topics

#ai-agent#rag#llm#java#spring-boot#vue3#mcp#langchain4j#agent#knowledge-base

FAQ

What is langchat?
Open-source AI agent application platform built on Java, LangChain4j, Spring Boot and Vue 3, covering models, agents, RAG, Skills, MCP and text-to-SQL analysis. LangChat is a modular AI agent application platform for building and running LLM-based apps on a Java and Vue stack. It connects multiple model providers such as OpenAI, Azure OpenAI, Anthropic, Gemini, DeepSeek, Qwen, Zhipu and Ollama through one configuration layer, and lets you assemble agents from a system prompt, knowledge bases, Skills and MCP services.
Is langchat free to use? What license does it have?
langchat is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is langchat still maintained?
Actively maintained. The last commit to langchat was on Sep 27, 2026.
What can I use langchat for?
Java teams building internal AI assistants on Spring Boot. Adding document question answering over company knowledge bases. Exposing agents through an OpenAI-compatible API to existing clients. Letting business users query databases in natural language with charts.
How do I install langchat?
Clone the repository (next branch): git clone -b next https://github.com/langchat/langchat.git Install frontend dependencies in langchat-ui: pnpm install Copy the local config example and fill in database settings: cp langchat-server/src/main/resources/application-local.example.yml langchat-server/src/main/resources/application-local.yml Start the project: SPRING_PROFILES_ACTIVE=local ./langchat.sh
Where can I get langchat?
The source code and installation instructions are on GitHub: https://github.com/LangChat/langchat

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects