MateClaw
[Website] [Live Demo] [Documentation] [δΈζ]
Other personal AI agents are built for one person. MateClaw is the one your IT department can actually sign off on.
Multi-user workspaces. Approval-gated sensitive actions. Full audit trail. Spring Boot Actuator health monitoring. Per-channel error isolation so one chat platform's outage doesn't take down the rest. One JAR on your own machine, zero data egress.
And underneath, a real agent harness. ReAct + Plan-and-Execute on a StateGraph runtime β not a one-shot RAG call dressed up. Tools, Skills, MCP, and ACP converge on one registry with per-employee binding. Sensitive tool calls flow through an approval gate you can actually inspect. Multi-vendor failover keeps the loop running when a provider doesn't.
Most AI tools die when their vendor has a bad day. Most forget you the moment the tab closes. Most give you a chatbox and call it a product.
MateClaw is the whole widget. One deployment. Reasoning, knowledge, memory, tools, channels β built together, not bolted on. And when your primary model goes down, the next one picks up mid-sentence.
Three things that make it different
1 Β· Your AI doesn't die when a model does
Primary key expired. Vendor returns 401. Network blip. Quota drained.
Other tools hand you a red error card. MateClaw routes to the next healthy provider β DashScope, OpenAI, Anthropic, Gemini, DeepSeek, Kimi, Ollama, LM Studio, MLX, 14+ in total β and the user sees the reply finish. A provider health tracker parks bad vendors in a cooldown window so they don't waste seconds on every turn.
You don't write a retry script. You drag providers into priority order in Settings β Models and watch the health dashboard fill with green dots as requests route around failures in real time.
2 Β· Knowledge that links itself
Upload a PDF, a batch of markdown, a scraped page β raw material in.
MateClaw's LLM Wiki digests it into structured pages, builds [[links]] between them, and remembers where every sentence came from. Click a citation, see the exact source chunk. Ask a question, the page you get is stitched from the right chunks β with references you can verify.
This is the difference between a warehouse and a library.
3 Β· One product, five surfaces
| Surface | What it is |
|---|---|
| Web Console | Full admin β digital employees, models, skills, knowledge, security, cron, runtime console (see what every employee is doing, force-recycle in one click) |
| Desktop | Electron app with a bundled JRE 21. Double-click, run. No Java install |
| Webchat Widget | One <script> tag embed. Drop it on any site |
| IM Channels | DingTalk Β· Feishu Β· WeChat Work Β· WeChat Β· Telegram Β· Discord Β· QQ Β· Slack |
| Plugin SDK | Java module for third-party capability packs |
Same brain. Same memory. Same tools. Different doors.
What's in the box
Digital employees, not chatbots
You hire coworkers, not chat boxes. Each one has a Role, a Goal, a Backstory, a pixel-art avatar, and a color of their own β five career templates ship ready (Product Researcher Β· Customer Support Β· Knowledge Curator Β· Data Analyst Β· Executive Assistant). ReAct drives iterative reasoning, Plan-and-Execute decomposes complex multi-step work, employees can delegate to one another in parallel. Dynamic context pruning, smart truncation, stale-stream cleanup β the boring stuff that makes long conversations actually work.
Knowledge & memory
- LLM Wiki β raw materials digest into linked pages with citations; the hot cache auto-injects into every employee's system prompt. Transformations engine (1.3.0+) turns the Wiki from a search index into a processing pipeline
- Workspace memory β
AGENTS.md,SOUL.md,PROFILE.md,MEMORY.md, daily notes - Memory lifecycle β post-conversation extraction, scheduled consolidation, Dreaming workflows. Workflows can also write directly into an employee's
MEMORY.mdvia thewrite_memorystep
Skills Β· MCP Β· ACP β three ways to extend capability
- SKILL.md packages β manifest + prompt + tool list + LESSONS.md (gets smarter the more you use it). Eight starter templates plus a five-step creation wizard, with Pre-flight checks that tell you what's missing before install
- MCP β stdio / SSE / Streamable HTTP, plug into any external tool server. Per-employee binding (1.3.0+) means a tool you install for one employee doesn't bleed into another's toolbox
- ACP β bring top-tier coding agents like Claude Code and Codex in as employees, auto-bridged to skill cards with wrapper tools
- Tool Guard β RBAC + approval flow + path protection. Capability needs boundaries
Business orchestration (1.3.0+)
- Workflow β compose multiple employees plus system actions (approval / channel dispatch / write-memory) into a publishable, triggerable, replayable linear DSL. Seven step modes (
sequential/fan_out/collect/conditional/await_approval/dispatch_channel/write_memory). JSON-first authoring with Monaco + schema validation, or natural-language β draft generation - Triggers β wire system events to workflows or to employee conversations. Six pattern types (
cron/webhook/channel_message/agent_lifecycle/content_match/workflow_completion). Default-on event governance: dedup, per-trigger rate limit, bot-self filter, recursion guard, fail-closed unknown patterns - Wiki Transformations β Wiki stops being retrieval-only. User-authored templates run against raw materials or existing pages, with cross-material map-reduce aggregation, reverse-citation extraction, JSON output mode, and per-template model picker
You see what every employee is doing
Admin Runtime Console (Settings β System β Runtime) β who's running, what step they're on, how many tokens, one-click force-recycle when stuck. Streaming is staged honestly (thinking / tool / answer), per-event SSE IDs make reconnects safe, multi-employee delegation no longer fights itself, long tasks demand evidence-grounded answers.
Multimodal creation
Text-to-speech Β· Speech-to-text Β· Image Β· Music Β· Video Β· 3D. First-class, not add-ons. Sidecar routing (1.3.0+) means a text-only main model + an image attachment no longer dead-ends β a configured vision model describes the image, and the main model answers. Image edit lands too: refer to an earlier conversation attachment by msg:<id>:<idx> and ask the model to recolor or restyle it. Four document-generation tools (DocxRenderTool / XlsxRenderTool / PptxRenderTool / PdfRenderTool) render Markdown straight to Office files inside the JVM β no subprocess, no Office install.
Enterprise-ready
RBAC + JWT. Personal Access Tokens for headless scripts and CI. HMAC-SHA-256 outbound webhook signing. Distributed Cron lock so multi-instance deployments don't double-fire. Full audit trail. Flyway-managed schema that auto-heals on upgrade. One JAR to ship. MySQL in production, H2 for dev β nothing to change in your code.
AI is becoming infrastructure
On March 2, 2026, Claude went dark for 4 hours across API, web, and mobile. Three weeks later, another 5 hours. Every company that bet their AI strategy on a single vendor spent those outages staring at red error cards.
This is the same shift databases went through around 2010 and cloud went through around 2018: the winning layer stops being tied to one supplier. 57% of companies now run AI agents in production. None of them want one vendor's bad day to become their bad day.
MateClaw is that layer β built the Spring Boot way.
Why MateClaw
| | MateClaw | OpenClaw | Hermes Agent | Claude Code | Cursor | |:---|:---:|:---:|:---:|:---:|:---:| | Multi-vendor failover | Chain + health tracker + cooldown | Swap providers via config | Orchestration w/ retry | Anthropic only | One model | | Knowledge digestion | LLM Wiki + page-level citations | Canvas + memory | Skills Hub + memory | β | Code index | | Multi-user admin | RBAC + approval + audit + runtime console