Logo
Deploy Now

SaaS Alternative

Relevance AI Microsoft Copilot

Categories

Developer Tools Workflow Automation MCP Team Collaboration AI Agent Platform Enterprise AI Multi-Agent Orchestration

Stars

1,026

Forks

314

Watchers

18

Developer links

Last Updated: 08-21-2026 02:16 PM (UTC)

MateClaw

MateClaw delivers a multi-agent AI platform where digital employees run as persistent team members with roles, goals, and accumulated skills rather than stateless chat completions. The Spring Boot backend on Spring AI Alibaba provides ReAct iterative reasoning and Plan-and-Execute decomposition on a StateGraph runtime, with parallel delegation between employees and dynamic context pruning for multi-step tasks. Five career templates ship ready (Product Researcher, Customer Support, Knowledge Curator, Data Analyst, Executive Assistant) while custom employees inherit configurable backstories, pixel-art avatars, and dedicated tool bindings. The MCP integration supports stdio, SSE, and Streamable HTTP transports with per-employee tool isolation preventing capability bleed between agents. ACP bridges bring Claude Code, Codex, and other coding agents in as first-class employees. Workflow orchestration composes multiple employees and system actions into publishable linear DSL processes with seven step modes: sequential, fan_out, collect, conditional, await_approval, dispatch_channel, and write_memory. The trigger system wires cron schedules, webhooks, channel messages, employee lifecycle events, content matches, and workflow completions to automated flows. The Admin Runtime Console provides real-time visibility into running employees with token usage tracking and one-click force-recycle. Spring Boot Actuator monitoring, full audit trail, and per-channel error isolation deliver production-grade reliability. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

MateClaw
MateClaw
MateClaw
MateClaw
MateClaw

Benefits

  • Team-Grade Multi-Agent With RBAC
  • Multi-user workspaces with role-based access control per employee, per model, and per tool. Approval gates pause risky actions for review with full audit trail.
  • Real Agent Reasoning Not Chat
  • ReAct and Plan-and-Execute on StateGraph runtime drive iterative reasoning with parallel delegation, not one-shot RAG calls wrapped in a conversational interface.
  • MCP With Per-Employee Isolation
  • Stdio, SSE, and Streamable HTTP MCP transports with per-employee tool binding prevent capability bleed — tools installed for one agent stay invisible to others.
  • One JAR Zero Data Egress
  • Single Spring Boot JAR deployment with embedded runtime requires no external dependencies beyond LLM API keys. All data stays on your infrastructure.

Features

  • Workflow DSL Orchestration
  • Seven step modes composing employees and system actions into triggerable linear processes with approval gates, parallel fan-out, and memory writes.
  • Digital Employee System
  • Persistent AI agents with roles, goals, backstories, dedicated skills, and accumulated LESSONS.md that improves performance through continued use.
  • Admin Runtime Console
  • Real-time dashboard showing employee status, current step, token usage, and one-click force-recycle for stuck agents across all running workflows.
  • Multi-Vendor LLM Failover
  • Automatic model switching across 14+ vendors when primary provider fails, resuming mid-conversation without user intervention or context loss.
  • ACP Coding Agent Bridge
  • Claude Code, Codex, and other coding agents auto-bridge as skill-card employees with wrapper tools and full integration into the workflow system.