What it does

Ask what went wrong with your own Ollama calls: lost prompt cache and the token where the prompt stopped matching, context overflow, a model running partly on CPU, tool schemas crowding the prompt. Last turn in numbers; which local models fit in video memory. Read-only.

Local connectionPricing not confirmedv0.8.12

Connection manifest

Public connection metadata from the source. Follow the provider’s setup guide for authentication, permissions, and required variables.

{
  "name": "io.github.LogneBudo/llmxray",
  "version": "0.8.12",
  "repository": {
    "url": "https://github.com/LogneBudo/llmxray"
  },
  "remotes": [],
  "packages": [
    {
      "registryType": "npm",
      "identifier": "llmxray",
      "version": "0.8.12",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "name": "LLMXRAY_URL",
          "isRequired": false
        },
        {
          "name": "OLLAMA_URL",
          "isRequired": false
        }
      ]
    }
  ]
}

Metadata reviewed for listing. Server code, permissions, and runtime behavior have not been security-audited. Directory access is free; individual providers may charge.