An intelligent multi-provider LLM assignment and routing system that optimizes AI agent workflows for cost, latency, and quality.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install oc-smart-agent-hub
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install oc-smart-agent-hub using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is OpenClaw Smart Agent Hub?
The OpenClaw Smart Agent Hub is a sophisticated multi-provider assignment system designed to streamline how AI agents interact with various Large Language Models. As a cornerstone of the Openclaw Skills ecosystem, it allows developers to bridge the gap between cloud-based providers like OpenAI and Anthropic and local deployments such as Ollama or vLLM. This skill focuses on abstracting the complexity of model management, providing a unified interface for model selection and execution.
By leveraging this tool within Openclaw Skills, users can implement a zero-code configuration approach to agent logic. It empowers agents to dynamically choose the best model based on the specific requirements of a task, ensuring that high-stakes reasoning is handled by powerful models while routine processing is offloaded to more economical alternatives.
OpenClaw Smart Agent Hub Use Cases
- Reducing operational expenses by routing simple queries to cost-effective local models via Openclaw Skills.
- Enhancing system reliability through automatic failover to backup providers when a primary API is unavailable.
- Privacy-centric workflows that prioritize local LLM discovery and usage for sensitive data processing.
- Dynamic model assignment for multi-agent systems where different agents require different intelligence tiers.
How OpenClaw Smart Agent Hub Works
- The hub initializes by loading provider configurations from a centralized YAML file.
- It performs an auto-discovery scan to identify active local model services like LM Studio or Ollama.
- When a task is received, the intelligent router analyzes the task type and optimization goals (cost, speed, or quality).
- The system assigns the task to the most suitable available provider and model.
- In the event of a provider error, the failover logic automatically re-routes the request to a pre-defined fallback model.
OpenClaw Smart Agent Hub Setup
To integrate this component of Openclaw Skills into your environment, first install the necessary Python dependencies:
pip install pyyaml requests
Verify your current model environment by listing available providers:
python skills/multi-provider-agents/scripts/provider_manager.py list-models
If you are running local models, use the scan command to integrate them automatically:
python skills/multi-provider-agents/scripts/provider_manager.py scan
OpenClaw Smart Agent Hub Data Schema & Taxonomy
The skill organizes its configuration and discovery data using a structured directory and file system:
| Component | Path / Format | Description |
|---|---|---|
| Model Config | config/models.yaml |
The primary registry for API keys, endpoints, and routing rules. |
| Provider Scripts | scripts/provider_manager.py |
CLI utility for managing the lifecycle of model providers. |
| Templates | examples/*.yaml |
Pre-configured templates for OpenAI, Anthropic, and local setups. |
| Documentation | docs/ |
Detailed technical specifications in English and Chinese. |
OpenClaw Smart Agent Hub Advanced Features
- Auto-Discovery: Automatically detects and configures local LLM instances running on the network.
- Zero-Code Orchestration: Modify agent routing behavior entirely through YAML without altering the underlying Python code.
- Multi-Criteria Routing: Advanced logic to balance cost, latency, and output quality across dozens of providers in Openclaw Skills.
- Provider Lifecycle Management: Simple CLI commands to enable, disable, or add new providers on the fly.
SKILL.md
Loading
Related Openclaw Skills
Praesidia
A powerful security and identity layer that enables agent verification, trust scoring, and real-time guardrail enforcement for AI systems.
Praesidia
A comprehensive security and identity layer for AI agents that enables trust verification, agent discovery, and real-time policy enforcement.
Praesidia
Praesidia is a comprehensive security and identity layer for AI agents, offering trust scoring, marketplace discovery, and automated guardrail enforcement.
OpenClaw Ticket Assistant
An intelligent assistant that automates the creation of support tickets by analyzing customer service chat screenshots.
EvidenceOps: Forensic Media Triage
A professional suite of Openclaw Skills for forensic-grade media triage that ensures data integrity and a verifiable chain of custody for digital evidence.
FastAPI Production Patterns
Accelerate backend development with production-ready FastAPI patterns for Pydantic v2, async workflows, and secure deployments.
Featured*
