Spring AI LoomAgent

Spring Boot AI Agent — an out-of-the-box solution that makes your app converse, remember, think, and act.

Features

7 Pillars: 💬 Chat · 📚 Knowledge · 📁 Files · 🔧 MCP · 🧠 Skill · 🎨 Canvas · 🛡 RBAC Platform: 🧠 Skill Market · Knowledge Market · 🎛 Admin Console Advanced: 🧩 Sub-tasks · ⏰ Scheduled tasks · 🖼 Multimodal — one dependency, batteries included.

• 💬 Streaming Chat — SSE multi-turn, collapsible reasoning, message copy/download; multimodal image + document mixed input
• 📚 RAG Knowledge Base — Multi-KB management, Tika parsing + vectorization, built-in H2-backed vector store (JVector HNSW in-memory index; swap in any Spring AI vector store)
• 🔧 MCP Tool Integration — Sync/async dual mode; available tools gated by role authorization, enabled per chat
• 🧠 Skill Market — DB-stored prompt templates, 3 sources (self-built / market-pulled / role-granted); approval flow (submit → PENDING → admin approve/reject, rejected re-submits archive the old row); pull rejects overwriting same-name USER_CREATED; remove blocked when market_skill_id is set; admin can create (lands APPROVED immediately) / edit / approve / reject; no version field. Skills call MCP via @tool_name. Frontend chat input supports / picker for precise skill selection.
• 🧩 Sub-tasks & ⏰ Scheduled Tasks — Delegate a slice of work to a synchronous "sub-model"; LLM-created schedules run as sub-tasks and survive restarts
• 🙋 AskUser Interactive Tool — the AI asks you questions inline in the chat stream via option cards (single-select / multi-select / custom input), then seamlessly continues after you answer; sub-tasks and scheduled tasks never interrupt you
• 🛡 RBAC — Two levels: user type (admin / user) + business roles; admin sees all, normal users get the union of their roles' grants
• 🎛 Admin Console — Sidebar SPA: users / roles / skill market / knowledge market / MCP descriptions / logs (formerly usage stats); admin-gated
• 📁 File Management — Disk storage + H2 metadata, upload / preview / download, chat-attachment bridging
• 🎨 Canvas Board — full-screen drawing modal: 6 drawing tools + 18 web-UI stencils (CRUD prototype skeleton pieces) with a select tool for move / resize / label editing; exports a white-background PNG as a chat attachment, forming a prototype workflow with multimodal models or the HTML render tool
• 🧰 Built-in Tools — universal (visible to every logged-in user): time / file / skill / knowledge / sub-task / schedule / askUser; RBAC-gated (admin grants per role): git / maven / end-to-end deploy / html-render; see TOOLS.md
• ⚙️ Batteries-included Engineering — Spring Boot auto-config, every bean replaceable via @ConditionalOnMissingBean, Flyway migrations, broad chat / embedding / vector-store support

Built-in Tools

All tools follow the interface + default implementation pattern. Every component is registered with @ConditionalOnMissingBean, allowing consumers to replace any piece with a custom implementation.

universal = visible to every logged-in user (@ToolGroup(defaultGranted=true)). RBAC = visible only after an admin grants the tool group to a role (role_tool table). The legacy *.enabled yml switches no longer gate any tool since M3 — see TOOLS.md §1.

For full @Tool method signatures, parameter details, and configuration reference, see TOOLS.md.

Admin Console

Standalone MCP Servers

File, Git, Maven, and Compile each have a standalone MCP server module — the core layer has no Spring dependency and can be deployed via jbang to any MCP-compatible agent (Claude Desktop, Cursor, etc.):

Quick Start: Add a Chat Interface

1. Add LoomAgent Dependency

<dependency>
 <groupId>io.github.wb04307201</groupId>
 <artifactId>spring-ai-loom-agent-spring-boot-starter</artifactId>
 <version>1.1.48</version>
</dependency>

2. Add a Spring AI Model Dependency

The test application uses Alibaba's Qwen (DashScope) via Spring AI Alibaba. Swap the dependency and config for any other provider:

<dependency>
 <groupId>com.alibaba.cloud.ai</groupId>
 <artifactId>spring-ai-alibaba-starter-dashscope</artifactId>
 <version>1.1.2.3</version>
</dependency>

spring:
  ai:
    dashscope:
      api-key: ${DASHSCOPE_API_KEY}
      chat:
        options:
          model: qwen3.7-plus
          multi_model: true
          enable_thinking: true

For other models, see the Spring AI docs.

Note: For document-based Q&A, ensure the model supports multimodal input (e.g., multi_model: true). Document content is injected via System Prompt.

3. Start the Project

Visit http://localhost:8080/spring/ai/loom

Document Upload & Conversation

Click the + button next to the input field to upload images or documents. After uploading, type your question and send it. Click the palette button right of + to open the drawing canvas: freehand drawing (pen / line / rectangle / ellipse / text / eraser, with color swatches, stroke width, undo/redo) plus 18 built-in web UI stencils in a categorized "Components ▾" panel — CRUD skeleton pieces (data table with comma-separated column headers, form field, action bar, pagination, tabs, dialog, status tag, switch, textarea, breadcrumb) and basic controls — all movable, resizable, double-click to edit labels, for quickly sketching admin CRUD prototypes; Confirm exports a white-background PNG that is attached to the message like any uploaded image (pairs with multimodal models or the HTML render tool for a prototype workflow).

Supported Document Formats

PDF, DOCX, XLSX, PPTX, MD, TXT, HTML, CSV, RTF, and more.

How It Works

1. Images: Passed as Media type directly to the multimodal model (requires model support, e.g., DashScope Qwen series)
2. Documents: Text content extracted via Apache Tika, injected as System Prompt into the conversation context
3. Mixed scenarios: Images and documents can be uploaded together; the model synthesizes visual information and document text

File Download, Preview, and Deletion

Uploaded and generated files can get download links via MCP tool downloadFileUrl, or preview links via MCP tool viewFileUrl. Files and directories