# Llmxray

> LLMxRay — Local LLM Observatory. Full observability interface for Ollama: chat, streaming, reasoning, RAG, introspection, metrics.

- Page: https://www.whatwemade.app/p/llmxray
- What it is: Web app (also MCP server), for engineering
- Made by: [Djovani](https://www.whatwemade.app/u/lognebudo)
- Run it yourself: get the code and run your own copy
- Live: https://lognebudo.github.io/llmxray
- Code: https://github.com/LogneBudo/llmxray (Apache-2.0, 28 stars)
- Tags: ai-agents, developer-tools, llm-observability, local-llm, logprobs
- Upvotes: 2, comments: 0

## About

See what your local AI is actually doing.

Point VS Code Copilot, Open WebUI, Continue, n8n or your own agent at LLMxRay instead of Ollama, and see every turn: what was cached, what was read again, what the daemon silently cut, which tool evicted which model. No cloud. No API keys. No cost.

🌐 English • Français • 中文 • العربية • Srpski

Quick Start • What your tools send • Send it on • For agents • Also in the box • Who is this for • Install • Ollama compatibility • Changelog

You need Ollama running with at least one model pulled (`ollama pull llama3.2`). Then:

## How it was made

- Claude Code, 100% of the work
- Claude, used by the app at runtime
- ChatGPT, used by the app at runtime
- Codex, used by the app at runtime
- Cursor, used by the app at runtime
- Gemini, used by the app at runtime
- Grok, used by the app at runtime
- Copilot, used by the app at runtime
- Stack: MCP SDK, Tailwind, TypeScript

## What you need to run it

- Tools: Node 22+

Shared on WhatWeMade: https://www.whatwemade.app/p/llmxray