QUICK START

ComputeGpu + Aider

GPU compute for aider. Same CLI, same MCP server.

Step 1: Install + Signup

npm install -g computegpu
computegpu signup you@company.com my-project

API key saved to ~/.computegpu/config.json. Owner verifies with $1 (credited to wallet).

Step 2: Add MCP Server

Add to your MCP config (.mcp.json or IDE settings):

{
  "mcpServers": {
    "computegpu": {
      "type": "stdio",
      "command": "computegpu",
      "args": ["mcp-serve"]
    }
  }
}

11 GPU tools discovered automatically: deploy, stop, destroy, types, cheapest, pods, status, resume, topup.

Step 3: Deploy a GPU

computegpu deploy --gpu "RTX 4090" --models llama3.3
computegpu pods
computegpu stop POD_ID