An advanced orchestration tool for routing Ollama inference requests across a network of Windows PCs to maximize hardware utilization.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install windows-ollama
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 windows-ollama 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 Windows Ollama Fleet Manager?
Windows Ollama Herd is a powerful tool designed to consolidate several Windows machines into a unified AI compute cluster. By leveraging Openclaw Skills, developers can transform a mix of gaming desktops, laptops, and workstations into a single high-performance API endpoint. This system automatically manages traffic distribution, ensuring that requests are routed to the most available or performant node in the fleet.
Built for the Windows ecosystem, it integrates natively with NVIDIA RTX GPUs and provides an OpenAI-compatible interface. Whether you are running Llama, DeepSeek, or Mistral, this skill simplifies the complexity of managing distributed local inference through a centralized router and a real-time health dashboard.
Windows Ollama Fleet Manager Use Cases
- Pooling GPU resources from multiple Windows desktops for large model inference
- Setting up a distributed AI lab using existing home or office hardware
- Improving inference reliability by load balancing requests across several nodes
- Creating a unified API endpoint for local LLM applications using Openclaw Skills
- Monitoring real-time GPU health and model status across a network
How Windows Ollama Fleet Manager Works
- The central Windows Ollama router is initialized using the herd command to listen for incoming API requests.
- Individual Windows PCs on the network run herd-node to register themselves as available compute resources.
- The router performs health checks and latency monitoring to determine the best node for each request.
- Users send standard Ollama or OpenAI-formatted requests to the central router URL.
- The system dynamically routes the inference task and returns the response to the client.
Windows Ollama Fleet Manager Setup
Prerequisites
Install Ollama on Windows from the official website and ensure Python is available.
Installation
Run the following command in your terminal:
pip install ollama-herd
Deployment
Start the router on your primary Windows PC:
herd
herd-node
On all other Windows nodes in the network:
herd-node --router-url http://<router-ip>:11435
Firewall Configuration
Allow incoming traffic through the designated port for communication:
netsh advfirewall firewall add rule name="Ollama Herd" dir=in action=allow protocol=tcp localport=11435
Windows Ollama Fleet Manager Data Schema & Taxonomy
| File/Path | Format | Purpose |
|---|---|---|
~/.fleet-manager/latency.db |
SQLite/DB | Tracks network latency and node performance |
~/.fleet-manager/logs/herd.jsonl |
JSONL | Logs fleet activity, request history, and errors |
/fleet/status |
JSON API | Provides a real-time list of all active Windows nodes |
/dashboard/api/health |
JSON API | Reports granular health metrics for monitoring |
Windows Ollama Fleet Manager Advanced Features
- Multi-agent support via a unified endpoint for complex Openclaw Skills workflows
- Native support for image generation and text embeddings across the entire fleet
- Persistent model loading configurations using OLLAMA_KEEP_ALIVE for instant response times
- mDNS auto-discovery for zero-configuration node registration on supported networks
- Real-time fleet health monitoring via an integrated web-based dashboard
SKILL.md
Loading
Related Openclaw Skills
Windows AI Local Inference Cluster
A powerful tool to turn your Windows PCs into a private, high-performance AI cluster for local LLM inference, image generation, and embeddings.
wsl2-local-ai
A high-performance LLM development stack for Windows users utilizing WSL2, NVIDIA GPU passthrough, and Ollama Herd routing.
photo-alchemy
A sophisticated AI pipeline that reimagines your personal photos as surrealist masterpieces using a multi-model workflow and deep macOS integration.
WeChat Message and File Sender
A comprehensive communication skill for Openclaw Skills that enables AI agents to query WeChat sessions and actively send text messages or various file types to contacts.
RTX Local AI
RTX Local AI turns your gaming PC into a high-performance local AI server, allowing you to run massive LLMs with zero cloud costs using NVIDIA RTX GPUs.
linux-ollama
A sophisticated fleet routing and load balancing solution for running Ollama across multiple Linux machines through a single unified endpoint.
Featured*
