Deploy a team of AI Agents in 5 minutes. Manager coordinates Workers, all visible in your IM.
HiClaw is an open-source Agent Teams system built on OpenClaw. A Manager Agent acts as your AI chief of staff — it creates Workers, assigns tasks, monitors progress, and reports back. You stay in control, making decisions instead of babysitting agents.
You → Manager → Worker Alice (frontend)
→ Worker Bob (backend)
→ Worker ...
All communication happens in Matrix Rooms. You see everything, and can intervene anytime — just like messaging a team in a group chat.
- 2026-03-10: HiClaw 1.0.4 released with CoPaw Worker support — 80% less memory, local host mode for browser automation. Read more on our blog.
- 2026-03-04: We officially open source HiClaw, an Agent Teams System. Read more on our blog.
Security by design: Workers never hold real API keys or GitHub PATs. They only carry a consumer token (like a badge). Even a compromised Worker can't leak your credentials.
Truly open IM: Built-in Matrix server means no Slack/Feishu bot approval process. Open Element Web in your browser, or use any Matrix client (Element, FluffyChat) on mobile — iOS, Android, Web.
One command to start: A single curl | bash sets everything up — Higress AI Gateway, Matrix server, file storage, web client, and the Manager Agent itself.
Skills ecosystem: Workers can pull from skills.sh (80,000+ community skills) on demand. Safe to use because Workers can't access real credentials anyway.
bash <(curl -sSL https://higress.ai/hiclaw/install.sh)That's it. The script asks for your LLM API key, then sets everything up. When it's done:
=== HiClaw Manager Started! ===
Open: http://127.0.0.1:18088
Login: admin / [generated password]
Tell the Manager: "Create a Worker named alice for frontend dev"
Windows (PowerShell 7+):
Set-ExecutionPolicy Bypass -Scope Process -Force; Invoke-Expression ((New-Object System.Net.WebClient).DownloadString('https://higress.ai/hiclaw/install.ps1'))Prerequisites: Docker Desktop (Windows/macOS) or Docker Engine (Linux). That's all.
- Docker Desktop (Windows / macOS)
- Docker Engine (Linux) or Podman Desktop (alternative)
Resource requirements: Minimum 2 CPU cores and 4 GB RAM. If you want to deploy multiple Workers for a more powerful Agent Teams experience, 4 CPU cores and 8 GB RAM are recommended — OpenClaw's memory usage is relatively high. In Docker Desktop, go to Settings → Resources to adjust.
Run the same install script in-place to upgrade. Your data and config are preserved. Upgrades to the latest version by default:
bash <(curl -sSL https://higress.ai/hiclaw/install.sh)To upgrade to a specific version:
HICLAW_VERSION=0.2.0 bash <(curl -sSL https://higress.ai/hiclaw/install.sh)
- Open
http://127.0.0.1:18088in your browser - Login with the credentials shown during install
- Tell the Manager to create a Worker and assign it a task
For mobile: download Element or FluffyChat, connect to your Matrix server address, and manage your agents from your phone.
The Manager handles the full Worker lifecycle through natural language:
You: Create a Worker named alice for frontend development
Manager: Done. Worker alice is ready.
Room: Worker: Alice
Tell alice what to build.
You: @alice implement a login page with React
Alice: On it... [a few minutes later]
Done. PR submitted: https://github.com/xxx/pull/1
① Manager creates a Worker and assigns tasks ② You can also direct Workers directly in the room
The Manager also runs periodic heartbeats — if a Worker gets stuck, it alerts you automatically.
Worker (consumer token only)
→ Higress AI Gateway (holds real API keys, GitHub PAT)
→ LLM API / GitHub API / MCP Servers
Workers only see their consumer token. The gateway handles all real credentials. Manager knows what Workers are doing, but never touches the actual keys either.
Every Matrix Room has you, the Manager, and the relevant Workers. You can jump in at any point:
You: @bob wait, change the password rule to minimum 8 chars
Bob: Got it, updated.
Alice: Frontend validation updated too.
No black boxes. No hidden agent-to-agent calls.
| 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 |
┌─────────────────────────────────────────────┐
│ hiclaw-manager-agent │
│ Higress │ Tuwunel │ MinIO │ Element Web │
│ Manager Agent (OpenClaw) │
└──────────────────┬──────────────────────────┘
│ Matrix + HTTP Files
┌──────────────────┴──────┐ ┌────────────────┐
│ hiclaw-worker-agent │ │ hiclaw-worker │
│ Worker Alice (OpenClaw)│ │ Worker Bob │
└─────────────────────────┘ └────────────────┘
| Component | Role |
|---|---|
| Higress AI Gateway | LLM proxy, MCP Server hosting, credential management |
| Tuwunel (Matrix) | 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 |
If the Manager container fails to start, check the agent log for details:
docker exec -it hiclaw-manager cat /var/log/hiclaw/manager-agent.logSee docs/zh-cn/faq.md for common issues (startup timeout, LAN access, etc.).
Feel free to open an issue or ask in Discord / DingTalk group.
Currently, Workers run on OpenClaw which has relatively high memory usage. We plan to support alternative lightweight runtimes:
- CoPaw ✅ Released in 1.0.4 — Lightweight agent runtime by AgentScope. Docker mode uses ~100MB (vs ~500MB for OpenClaw), plus local host mode for browser automation and local file access.
- ZeroClaw — Rust-based ultra-lightweight runtime, 3.4MB binary, <10ms cold start, designed for edge and resource-constrained environments
- NanoClaw — Minimal OpenClaw alternative, <4000 LOC, container-based isolation, built on Anthropic Agents SDK
Goal: Reduce per-Worker memory footprint from ~500MB to <100MB, enabling more Workers on the same hardware.
A built-in dashboard for observing and controlling your Agent Teams:
- Real-time observation: Watch each agent's thinking process, tool calls, and decision-making
- Active interruption: Pause or stop any agent mid-task when you spot issues
- Task timeline: Visual history of who did what and when
- Resource monitoring: CPU/memory usage per Worker
Goal: Make Agent Teams as observable and controllable as human teams — no black boxes.
Currently, Workers access GitHub via Higress MCP Gateway + mcporter, using only a Higress-issued token — real GitHub PATs never leave the gateway. This secure pattern works for any MCP server:
- Pre-built MCP connectors: GitHub, Slack, Notion, Linear, and more
- Custom MCP integration: Bring your own MCP server, let Higress handle auth
- Per-Worker access control: Manager grants/revokes MCP access per Worker
Goal: Any tool that speaks MCP can be safely exposed to Workers without credential leakage.
| docs/quickstart.md | Step-by-step guide with verification checkpoints |
| docs/architecture.md | System architecture deep dive |
| docs/manager-guide.md | Manager configuration |
| docs/worker-guide.md | Worker deployment and troubleshooting |
| docs/development.md | Contributing and local dev |
Chinese docs: docs/zh-cn/ — including FAQ
make build # Build all images
make test # Build + run all integration tests
make test SKIP_BUILD=1 # Run tests without rebuilding
make test-quick # Smoke test only (test-01)# Send a task to Manager via CLI
make replay TASK="Create a Worker named alice for frontend development"
# Uninstall everything
make uninstall
# Push multi-arch images
make push VERSION=0.1.0 REGISTRY=ghcr.io REPO=higress-group/hiclaw
make help # All available targets- Discord
- DingTalk Group
- WeChat Group — scan to join:
Apache License 2.0