⚡ Become a Compute Provider with NexusWorker

Monetize your idle GPU compute by serving open-source AI inference on the NexusCompute decentralized network.

Whether you have a single gaming PC (NVIDIA RTX 3060/4090), an Apple Silicon Mac (M1/M2/M3/M4), or a dedicated mining rig / GPU cluster, NexusWorker enables you to earn revenue passively by serving inference requests for open models like Llama 3, DeepSeek-R1, and Mistral.

💡 Why Provide Compute on NexusCompute?

• 💰 Passive Income: Earn revenue for every prompt token and completion token your GPU processes.
• 🔒 100% Secure & Outbound-Only: Zero inbound open ports, no port forwarding, and no router configuration needed. The daemon connects outbound to Cloudflare Edge.
• 🛡️ Completely Sandboxed: Only communicates with your local inference backend (Ollama / vLLM) over 127.0.0.1.
• ⚡ 1-Minute Setup: Install in a single command with pip install nexus-worker.
• 🖥️ Full Cross-Platform Support: Runs seamlessly on Windows, Linux, and macOS.
• ⏸️ You're in Control: Start, pause, or stop whenever you need your GPU for gaming or work (Ctrl + C).

🚀 Provider Quickstart Guide (Under 3 Minutes)

Step 1: Get Your Node Token

1. Open the NexusCompute Provider Portal.
2. Go to the Provider Dashboard and click Become a Provider or Register Node.
3. Copy your unique Node Token (e.g., nx-node-0a0a3b29ed...).

Step 2: Ensure Your Local Engine is Running

We recommend Ollama for the easiest 1-click setup:

1. Install Ollama and pull any model you want to serve:

   ollama pull llama3:8b
   ollama pull deepseek-r1:7b
   

2. Verify Ollama is running at http://localhost:11434.

(Note: vLLM is also supported for high-throughput enterprise setups).

Step 3: Install & Start Serving

Open your terminal (PowerShell, Command Prompt, or Terminal on macOS/Linux) and run:

# 1. Install the official provider daemon from PyPI
pip install nexus-worker

# 2. (Optional) Check your detected GPU & available local models
nexus-worker info

# 3. Start earning!
nexus-worker start --token nx-node-YOUR_TOKEN_HERE

That's it! Your node will register with the network, begin long-polling for inference tasks, stream responses back to users, and track your earnings on your live dashboard.

🛠️ CLI Reference for Providers

nexus-worker start

Connects your machine to the NexusCompute coordinator network and begins processing jobs.

Example:

nexus-worker start --token nx-node-0a0a3b29ed4e323af354549a6681821a1b75157e

nexus-worker info

Scans and displays your local system specs (GPU model, VRAM, and discovered models ready to serve):

nexus-worker info

❓ Frequently Asked Questions (FAQ) for Providers

💻 Developer Installation (From Source)

If you wish to contribute to the open-source provider daemon codebase:

git clone https://github.com/nexus-compute-ai/nexus-worker.git
cd nexus-worker

# Setup virtual environment
python -m venv .venv
source .venv/bin/activate  # Or .\.venv\Scripts\activate on Windows

# Install in editable mode
pip install -e .

📄 License

Distributed under the MIT License. See LICENSE for more details.