by LangChat
LangChat 是由 LangChat Team 开发的开源 AI Agent 应用平台,支持多模型、Agent、知识库 RAG、Skills、MCP 与智能问数。
# Add to your Claude Code skills
git clone https://github.com/LangChat/langchatLast scanned: 9/27/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-09-27T09:50:14.262Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how langchat compares with popular alternatives.
langchat is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by LangChat. LangChat 是由 LangChat Team 开发的开源 AI Agent 应用平台,支持多模型、Agent、知识库 RAG、Skills、MCP 与智能问数。. It has 1,286 GitHub stars.
Yes. langchat passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/LangChat/langchat" and add it to your Claude Code skills directory (see the Installation section above).
langchat is primarily written in Vue. It is open-source under LangChat on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh langchat against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
LangChat Agentic 是 LangChat Team 面向企业采购、交付与长期运营推出的商业产品。商业版拥有比当前开源版本更丰富、完整的产品能力,适合需要将 AI 应用规模化部署到真实业务流程中的组织。
商业版主要提供:
如果你正在进行企业级 AI 平台选型或采购,建议优先了解 LangChat Agentic:
查看商业版完整能力 · 阅读商业白皮书 · 查看价格与交付方案 · 了解团队
LangChat 是一个模块化、可扩展的开源 AI Agent 应用平台。它将模型接入、Agent 构建、知识库 RAG、Skills、MCP、数据分析和权限管理整合到同一套 Java 与 Vue 技术体系中,帮助开发者快速搭建可运行、可集成的 AI 应用。
开源版本适合技术验证、二次开发和团队内部场景建设。项目采用模块化单体架构,在保持部署简单的同时,为后续按领域拆分和能力扩展保留清晰边界。
| 能力 | 说明 |
|---|---|
| 多模型接入 | 统一管理 OpenAI、Azure OpenAI、Anthropic、Gemini、DeepSeek、通义千问、智谱、Ollama 及 OpenAI 兼容服务 |
| Agent 构建 | 配置模型、系统提示词、知识库、Skills 与 MCP,提供构建、调试和运行界面 |
| 对话运行时 | 支持会话与消息管理、SSE 流式响应,并提供 OpenAI 兼容的 Chat Completions 接口 |
| 知识库 RAG | 管理知识库、文档上传、解析预览、分段、索引状态和向量存储配置 |
| Skills 扩展 | 支持技能包或文件夹上传、文件浏览、下载和运行时工具注册 |
| MCP 集成 | 管理外部 MCP 服务配置,并在 Agent 运行时复用客户端会话 |
| 智能问数 | 接入数据源、读取结构目录,以自然语言生成分析结果与图表 |
| 图像能力 | 提供图像生成与图像识别接口,复用统一模型配置体系 |
| 应用市场 | 发布和发现 Agent,并从统一聊天界面直接运行应用 |
| 权限与治理 | 提供登录、用户、角色、菜单、动态路由与 RBAC 权限管理 |
以下截图来自本地开发环境启动后的实际界面,按功能分类展示。信息密度较高的页面(Agent 构建器、文档导入、数据源详情)采用一行两张,其余一行三张。
flowchart LR
U[用户 / 外部系统] --> UI[Vue 3 管理端]
U --> API[REST / OpenAI-compatible API]
UI --> API
API --> AUTH[langchat-auth<br/>认证与 RBAC]
API --> AIGC[langchat-aigc<br/>配置与资源管理]
API --> CORE[langchat-core<br/>Agent / Chat / RAG / Skills]
API --> DS[langchat-datasource<br/>数据源与智能问数]
CORE --> LLM[模型服务<br/>OpenAI / Gemini / Ollama / ...]
CORE --> MCP[MCP 服务与工具]
CORE --> VECTOR[Pgvector / Milvus]
AIGC --> MYSQL[(MySQL)]
AUTH --> MYSQL
DS --> DATA[(业务数据源)]
| 层级 | 主要技术 |
|---|---|
| 后端 | Java 17、Spring Boot 3.3、LangChain4j 1.12、MyBatis-Plus、Sa-Token |
| 前端 | Vue 3、TypeScript、Vite、Pinia、Naive UI、Tailwind CSS、VXE Table、ECharts |
| 数据 | MySQL、PostgreSQL / Pgvector、Milvus |
| 工程 | Maven 多模块、pnpm workspace、SSE、OpenAI-compatible API |
langchat
├── build-release.sh # 构建后端、前端并生成非 Docker 交付目录
├── build-docker.sh # Docker 配置准备、镜像构建与服务管理入口
├── langchat-common # 公共基础能力与依赖管理
├── langchat-auth # 认证、用户、角色、菜单与权限
├── langchat-aigc # 模型、Agent、知识库、Skills 等业务管理
├── langchat-core # 对话运行时、RAG、MCP、图像与数据分析
├── langchat-datasource # 数据源接入、结构读取与查询能力
├── langchat-server # Spring Boot 启动与应用配置
├── langchat-ui