ClawManager provides a Kubernetes-native control plane for managing OpenClaw and Linux desktop runtimes at scale. It targets administrators and teams needing centralized deployment, operation, and access to desktop environments within a Kubernetes cluster, offering secure browser-based access and integrated AI model governance. The primary benefit is a unified platform for managing user access, resource quotas, and runtime images, simplifying desktop provisioning and AI gateway control.

How It Works

ClawManager operates as a Kubernetes-first control plane, deploying and managing desktop runtimes directly within the cluster. Its architecture features a frontend/backend service interacting with the Kubernetes API, MySQL for state storage, and providing secure, token-based access via a backend proxy. This approach keeps desktop services internal to the cluster network, enhancing security. A key differentiator is the integrated AI Gateway, which acts as a governance layer for model access, offering policy enforcement, end-to-end auditing, cost accounting, and risk controls on top of various upstream and local model providers.

Quick Start & Requirements

• Primary install: Apply the bundled manifest: kubectl apply -f deployments/k8s/clawmanager.yaml.
• Prerequisites: A working Kubernetes cluster where kubectl get nodes functions correctly.
• Build from Source: Requires frontend (npm install, npm run build) and backend (go mod tidy, go build) steps. Docker image build available (docker build -t clawmanager:latest .).
• Default Accounts: admin / admin123. Imported admin/regular users default to admin123 and user123 respectively.
• Links: No external quick-start or demo links provided beyond the README.

Highlighted Details

• Comprehensive instance lifecycle management (create, start, stop, restart, delete, inspect, sync).
• Support for diverse runtime types including OpenClaw, Webtop, Ubuntu, Debian, CentOS, and custom images.
• AI Gateway provides OpenAI-compatible endpoints with model management, policy, audit trails, cost tracking, and risk controls for numerous providers (OpenAI, Zhipu AI, Groq, etc.) and local endpoints.
• Robust user management via CSV bulk import, supporting detailed quota controls for CPU, memory, storage, and GPU.
• Multilingual user interface.

Maintenance & Community

No specific details regarding maintainers, community channels (e.g., Discord, Slack), sponsorships, or roadmap are present in the provided README.

Licensing & Compatibility

• License: MIT License.
• Compatibility: The MIT license is permissive and generally compatible with commercial use and linking in closed-source projects.

Limitations & Caveats

The project description field is explicitly marked as "None". No other specific limitations, alpha status, known bugs, or unsupported platforms are detailed in the provided README.