LangChain4J AIDeepin
基于AI的工作效率提升工具（聊天、绘画、知识库、工作流、 MCP服务市场、语音输入输出、长期记忆） | Ai-based productivity tools (Chat,Draw,RAG,Workflow,MCP marketplace, ASR,TTS, Long-term memory etc)
What is LangChain4J AIDeepin?
LangChain4J AIDeepin is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 基于ai的工作效率提升工具（聊天、绘画、知识库、工作流、 mcp服务市场、语音输入输出、长期记忆） | ai-based productivity tools (chat,draw,rag,workflow,mcp marketplace, asr,tts, long-term memory etc)
基于AI的工作效率提升工具（聊天、绘画、知识库、工作流、 MCP服务市场、语音输入输出、长期记忆） | Ai-based productivity tools (Chat,Draw,RAG,Workflow,MCP marketplace, ASR,TTS, Long-term memory etc)
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 基于AI的工作效率提升工具（聊天、绘画、知识库、工作流、 MCP服务市场、语音输入输出、长期记忆） | Ai-based
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx langchain4j-aideepinConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use LangChain4J AIDeepin
LangChain4J AIDeepin is a comprehensive AI productivity platform built on Spring Boot and LangChain4J that provides a self-hostable environment combining multi-model chat, knowledge base management with Graph RAG, visual AI workflow design, text-to-image generation, and bidirectional voice (ASR/TTS) — all in one application. It exposes an MCP service marketplace so that both the platform itself and external MCP clients can consume its tools, and integrates with a wide range of AI providers including OpenAI, Qwen, DeepSeek, SiliconFlow, and Ollama. Teams and individuals who want a self-hosted alternative to commercial AI platforms, with long-term memory and workflow automation baked in, use AIDeepin as their central AI operations hub.
Prerequisites
- Java 17+ and Maven or Gradle for building the Spring Boot backend
- Node.js 18+ for building the Vue 3 frontend (admin dashboard and user UI)
- Docker and Docker Compose recommended for the full-stack deployment (includes PostgreSQL, Redis, and vector store dependencies)
- At least one AI provider API key: OpenAI, Qwen (Alibaba Cloud), DeepSeek, SiliconFlow, or a local Ollama installation
- PostgreSQL database and a supported vector store (pgvector recommended for knowledge base features)
Clone the repository
Clone the AIDeepin monorepo which contains the backend and both frontend applications.
git clone https://github.com/moyangzhan/langchain4j-aideepin.git
cd langchain4j-aideepinConfigure the application
Copy the example application config and fill in your database credentials, AI provider API keys, and vector store settings.
cp aideepin-web/src/main/resources/application-example.yml \
aideepin-web/src/main/resources/application.yml
# Edit application.yml with your settings:
# spring.datasource.url, spring.datasource.username, spring.datasource.password
# AI provider keys (openai.api-key, qwen.api-key, etc.)
# Vector store connection settingsDeploy with Docker Compose (recommended)
Use Docker Compose to start the full stack including the backend, PostgreSQL, pgvector, Redis, and the frontend apps.
cd docker
cp .env.example .env
# Edit .env with your API keys and passwords
docker compose up -dOr build and run manually
Build and run the Spring Boot backend, then build the Vue 3 frontends separately.
# Build the backend
mvn clean package -DskipTests
java -jar aideepin-web/target/aideepin-web-*.jar
# Build admin UI
cd aideepin-admin && npm install && npm run build
# Build user UI
cd aideepin-ui && npm install && npm run buildAccess the platform and configure AI models
Open the admin dashboard (default: http://localhost:9001/admin) and configure your AI model providers, knowledge bases, and workflow settings through the UI.
Connect via MCP
AIDeepin exposes an MCP endpoint. Add it to your MCP client config to use its knowledge base and workflow tools from Claude Desktop or other clients.
{
"mcpServers": {
"aideepin": {
"url": "http://localhost:9001/mcp",
"headers": {
"Authorization": "Bearer <your-aideepin-api-key>"
}
}
}
}LangChain4J AIDeepin Examples
Client configuration
MCP client config to connect to a self-hosted AIDeepin instance.
{
"mcpServers": {
"aideepin": {
"url": "http://localhost:9001/mcp",
"headers": {
"Authorization": "Bearer <your-aideepin-api-key>"
}
}
}
}Prompts to try
Example prompts for using AIDeepin's AI capabilities through an MCP-connected assistant.
- "Search the knowledge base for documents about our Q3 product roadmap"
- "Create a new knowledge base entry from this document and index it for vector search"
- "Run the 'customer-onboarding' workflow with this input data"
- "Generate an image of a futuristic cityscape using the configured image model"
- "Transcribe this audio file and add the result to the knowledge base"
- "List all available AI models configured in AIDeepin and their capabilities"Troubleshooting LangChain4J AIDeepin
Backend fails to start with database connection errors
Verify PostgreSQL is running and the credentials in application.yml match your database setup. If using pgvector, ensure the extension is installed: run 'CREATE EXTENSION IF NOT EXISTS vector;' in your PostgreSQL database.
Knowledge base search returns no results or vector store errors
The vector store (pgvector or alternative) must be initialized before indexing. Check that the embedding model is correctly configured in application.yml and that the AI provider API key for embeddings is valid. Re-index the knowledge base through the admin UI after fixing configuration.
MCP endpoint is not reachable from the client
Confirm the Spring Boot backend is running on the expected port (default 9001). Check that CORS is configured to allow connections from your MCP client host. Generate an API key from the AIDeepin admin dashboard under Settings → API Keys and use it in the Authorization header.
Frequently Asked Questions about LangChain4J AIDeepin
What is LangChain4J AIDeepin?
LangChain4J AIDeepin is a Model Context Protocol (MCP) server that 基于ai的工作效率提升工具（聊天、绘画、知识库、工作流、 mcp服务市场、语音输入输出、长期记忆） | ai-based productivity tools (chat,draw,rag,workflow,mcp marketplace, asr,tts, long-term memory etc) It connects AI assistants to external tools and data sources through a standardized interface.
How do I install LangChain4J AIDeepin?
Follow the installation instructions on the LangChain4J AIDeepin GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with LangChain4J AIDeepin?
LangChain4J AIDeepin works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is LangChain4J AIDeepin free to use?
Yes, LangChain4J AIDeepin is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
LangChain4J AIDeepin Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to LangChain4J AIDeepin? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up LangChain4J AIDeepin in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use LangChain4J AIDeepin?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.