alibaba / hiclaw
An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.
AI Architecture Analysis
This repository is indexed by RepoMind. By analyzing alibaba/hiclaw in our AI interface, you can instantly generate complete architecture diagrams, visualize control flows, and perform automated security audits across the entire codebase.
Our Agentic Context Augmented Generation (Agentic CAG) engine loads full source files into context on-demand, avoiding the fragmentation of traditional RAG systems. Ask questions about the architecture, dependencies, or specific features to see it in action.
Embed this Badge
Showcase RepoMind's analysis directly in your repository's README.
Repository Overview (README excerpt)
Crawler viewEnglish | δΈζ **HiClaw is an open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.** Built with a **Manager-Workers architecture**, HiClaw lets you coordinate multiple Worker Agents through a Manager Agent to complete complex tasks β all conversations are visible in Matrix rooms, and you can intervene at any time. Think of it as your AI team in a chat room: tell the Manager what you need, it spins up Workers, and you watch everything happen in real-time. Key Features β’ π¦ **Customizable "Claws"**: Each Claw can be OpenClaw, CoPaw, NanoClaw, ZeroClaw, or your own enterprise agent. Pre-installed with OpenClaw. ⒠𧬠**Manager Claw Role**: A dedicated Manager handles Worker lifecycle β create, assign tasks, monitor progress β all through natural language. β’ βοΈ **Private & Secure Matrix Communication**: Self-hosted Matrix server (Tuwunel) + Element Web client. **No third-party IM platforms, no external APIs, no data leaving your infrastructure.** Your agent conversations stay on your servers. β’ π¦ **Shared File System (MinIO)**: Centralized file storage for agent collaboration. Workers are stateless β destroy and recreate anytime. β’ π **Secure Entry via Higress AI Gateway**: Workers never hold real API keys. They only get consumer tokens. Even if compromised, attackers get nothing useful. News β’ **2026-03-14**: HiClaw 1.0.6 β enterprise-grade MCP Server management, zero credential exposure. Blog β’ **2026-03-10**: HiClaw 1.0.4 β CoPaw Worker support, 80% less memory. Blog β’ **2026-03-04**: HiClaw open sourced. Announcement Why HiClaw β’ **Enterprise-Grade Security**: Worker Agents operate with consumer tokens only. Real credentials (API keys, GitHub PATs) stay in the gateway β Workers can't see them, and neither can attackers. β’ **Fully Private**: Matrix is a decentralized, open protocol. Host it yourself, federate with others if you want. No vendor lock-in, no data harvesting. β’ **Human-in-the-Loop by Default**: Every Matrix room includes you, the Manager, and the relevant Workers. Watch everything. Jump in anytime. No black boxes. β’ **Zero Configuration IM**: Built-in Matrix server means no bot applications, no API approvals, no waiting. Just open Element Web and start chatting. β’ **One Command Setup**: and you're done β AI gateway, Matrix server, file storage, web client, and Manager Agent. β’ **Skills Ecosystem**: Workers pull from skills.sh (80,000+ community skills) on demand. Safe because Workers can't access real credentials. Quick Start **Prerequisites**: Docker Desktop (Windows/macOS) or Docker Engine (Linux). **Resources**: 2 CPU cores + 4 GB RAM minimum. For multiple Workers, 4 cores + 8 GB recommended. Install **macOS / Linux:** **Windows (PowerShell 5+):** The installer walks you through: β’ Choose your LLM provider (OpenAI-compatible APIs supported) β’ Enter your API key β’ Select network mode (local-only or external access) β’ Wait for setup to complete Access Open http://127.0.0.1:18088 in your browser and log in to Element Web. The Manager will greet you and explain how to create your first Worker. **Mobile**: Use any Matrix client (Element, FluffyChat) and connect to your server address. **That's it.** No bot applications. No external services. Your AI team runs entirely on your machine. Upgrade How It Works Manager as Your AI Chief of Staff β Manager creates a Worker and assigns tasks β‘ You can also direct Workers directly in the room Security Model Workers see only their consumer token. The gateway handles all real credentials. The Manager knows what Workers are doing but never touches the actual keys. Human in the Loop Every Matrix Room includes you, the Manager, and relevant Workers: No hidden agent-to-agent calls. Everything is visible and intervenable. Architecture | Component | Role | |-----------|------| | Higress AI Gateway | LLM proxy, MCP Server hosting, credential management | | Tuwunel (Matrix) | Self-hosted IM server for all Agent + Human communication | | Element Web | Browser client, zero setup | | MinIO | Centralized file storage, Workers are stateless | | OpenClaw | Agent runtime with Matrix plugin and skills | HiClaw vs OpenClaw Native | | OpenClaw Native | HiClaw | |---|---|---| | Deployment | Single process | Distributed containers | | Agent creation | Manual config + restart | Conversational | | Credentials | Each agent holds real keys | Workers only hold consumer tokens | | Human visibility | Optional | Built-in (Matrix Rooms) | | Mobile access | Depends on channel setup | Any Matrix client, zero config | | Monitoring | None | Manager heartbeat, visible in Room | Roadmap β Released β’ ~~**CoPaw** β Lightweight agent runtime~~ Released in 1.0.4: ~150MB memory usage (vs ~500MB for OpenClaw), plus local host mode for browser automation. β’ ~~**Universal MCP Service Support** β MCP server integration~~ Released in 1.0.6: Any MCP server can be safely exposed to Workers through the gateway. Workers access tools using only Higress-issued tokens; real credentials never leave the gateway. In Progress Lightweight Worker Runtimes β’ **ZeroClaw** β Rust-based ultra-lightweight runtime, 3.4MB binary, <10ms cold start. β’ **NanoClaw** β Minimal OpenClaw alternative, <4000 LOC, container-based isolation. Goal: Reduce per-Worker memory from ~500MB to <100MB. Planned Team Management Center A built-in dashboard for observing and controlling your Agent Teams β real-time observation, active interruption, task timeline, resource monitoring. --- Documentation | | | |---|---| | docs/quickstart.md | Step-by-step guide | | docs/architecture.md | System architecture deep dive | | docs/manager-guide.md | Manager configuration | | docs/worker-guide.md | Worker deployment | | docs/development.md | Contributing and local dev | Troubleshooting See docs/zh-cβ¦