A Spring Boot AI assistant that wires ReAct agents, MCP protocol, and seven chat platforms into one stack. · matevip/mateclaw
Why This Matters Right Now
The multi-agent gold rush has been almost exclusively a Python story. LangChain, CrewAI, AutoGen — they all assume you live in a pip-install world. Meanwhile, the overwhelming majority of enterprise backends are Java. Spring Boot shops have been left watching the agentic AI wave roll past them, duct-taping Python microservices to their JVM monoliths just to get a ReAct loop running.
MateClaw is a direct answer to that gap. It's a full-stack AI assistant framework built on Java 17+ and Vue 3, powered by Spring AI Alibaba — and it ships with multi-agent orchestration, MCP protocol support, multi-layer memory, and adapters for seven messaging platforms out of the box. At 13 stars it's barely on anyone's radar. That's exactly when you want to be paying attention.
What It Actually Does
Let's be concrete, because "AI assistant" means nothing in 2025 without specifics.
MateClaw runs two agent execution modes. The first is ReAct — the classic Thought → Action → Observation loop that lets an agent reason through tool use iteratively. The second is Plan-and-Execute, which decomposes a complex user request into ordered sub-steps before execution begins. You can create multiple independent agents, each with its own persona, toolset, and memory scope. This isn't a single chatbot with a system prompt — it's a configurable agent fleet.
The tool system is layered. Built-in tools cover web search and date/time. Beyond that, MateClaw implements the MCP (Model Context Protocol), with GitHub and Filesystem MCP servers pre-configured — you enable them and they're live. Additional skill packages can be installed from ClawHub, which appears to be a first-party marketplace for extending agent capabilities. Custom MCP sources are also supported.
Memory is handled in four layers: a short-term context window with auto-compression, event-driven post-conversation memory extraction, workspace files (PROFILE.md, MEMORY.md, and daily notes that agents can read and write), and scheduled memory consolidation. The file-based memory approach is pragmatic — it's inspectable, version-controllable, and doesn't require a vector database to get started.
Channel support is genuinely broad: web console, DingTalk, Feishu, WeChat Work, Telegram, Discord, and QQ. The multi-channel adapter architecture means one configured agent can respond across all of them simultaneously.
Model support covers 20+ providers: OpenAI, Anthropic, Google Gemini, DeepSeek, DashScope, Kimi, MiniMax, Zhipu AI, Ollama, LM Studio, OpenRouter, and more. Provider configuration is handled through the web UI rather than raw config files, which lowers the operational friction significantly.
Technical Deep-Dive
The backend is mateclaw-server, a Spring Boot 3.5 application targeting Java 17+. It uses Maven (mvnw is included) and defaults to H2 for local development — the H2 console is exposed at http://localhost:18088/h2-console, which means zero database setup friction for first-run evaluation. SpringDoc OpenAPI is integrated for API documentation.
The frontend lives in mateclaw-ui, built with Vue 3 and pnpm. There's also an Electron wrapper for desktop distribution with auto-update support — so this isn't just a dev tool, it's aiming at end-user deployability.
The Spring AI Alibaba foundation is worth noting. This is Alibaba's Spring-native AI framework, meaning the agent orchestration primitives are built on top of Spring's dependency injection and configuration model. If you're a Spring developer, the mental model for extending agents with new tools or memory backends will feel familiar rather than foreign.
The topics list in the repository — react-agent, plan-and-execute, mcp-protocol, tool-calling, skills, multi-agent — maps almost one-to-one with the architectural layers described in the README. This isn't vaporware labeling; the feature surface appears genuinely implemented.
Starting the backend is straightforward:
bash
cd mateclaw-server
export DASHSCOPE_API_KEY=your-key-here
mvn spring-boot:run
The DashScope key requirement is the one friction point for Western developers — you'll want to swap in OpenAI or Ollama credentials instead, both of which are supported.
Honest Limitations
Let's not oversell this. 13 stars and a recent first push means the community and documentation are thin. The docs site exists (claw.mate.vip/docs) but the depth of that documentation is unverified. For production use, you're likely pioneering rather than following a well-worn path.
The Spring AI Alibaba dependency is a double-edged sword. It gives you Spring-native ergonomics, but it also means you're tied to an Alibaba-maintained framework that may have slower Western community support and could diverge from upstream Spring AI in ways that create long-term maintenance headaches.
The default DashScope API key requirement in the quick-start guide subtly signals that the primary author's context is the Chinese developer ecosystem. The platform integrations (DingTalk, Feishu, WeChat Work, QQ) confirm this. Western developers building for Slack, Teams, or linear workflows will need to implement their own channel adapters.
The ClawHub skill marketplace is mentioned but appears nascent. An ecosystem that doesn't exist yet is a bet, not a feature.
Who should NOT use this: Teams without Java expertise, anyone needing battle-tested production reliability today, or developers who need deep Slack/Teams integration out of the box. Also avoid if your organization can't tolerate dependencies on Alibaba-maintained OSS.
Verdict
MateClaw is the project Java shops have been quietly waiting for. If your backend is Spring Boot, your agents don't have to live in a separate Python sidecar anymore. The architecture is legitimately sophisticated — Plan-and-Execute orchestration, MCP protocol support, and file-based multi-layer memory are not trivial features, and they're packaged with the ergonomics Java developers expect.
The right early adopters are: backend engineers at enterprises with Java-first stacks who want to prototype agentic workflows without leaving the JVM, developers building internal productivity tools for Chinese enterprise platforms (DingTalk, Feishu), and Spring AI experimenters who want a reference architecture more complete than a tutorial.
At 13 stars, you're not late. You're early. The question is whether the team behind it sustains the momentum — and that's always the bet with early-stage OSS.
The multi-agent gold rush has been a Python-only story — MateClaw is the first credible attempt to bring ReAct orchestration and MCP protocol natively into the Spring Boot world.
Top comments (0)