LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.
llm repositories
Hand-picked tools to improve your workflow.
The open source codebase powering HuggingChat
The Open Standard for Generative UI
List of Permanent Free LLM API (API Keys)
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization
An open, programmable decision layer for models and compute.
Autonomous Hacking Agent for Red Team
Build distributed, production-grade, long-running agents.
企业级 Agentic RAG 智能体 - 全链路覆盖文档解析、多路检索、意图识别、问题重写、会话记忆、MCP 工具调用与深度思考。面向真实业务场景,从 0 到 1 完整工程实现。
Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3. Speaks MCP, A2A, and AG-UI.
Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp.