LLMxRay
Local observability interface for Ollama to chat, inspect prompts, and view cache and latency metrics.
Tested on Linux
Use it
Linux x86_64
You need first
- System packages:
Ollama
Install llmxray globally via npm
npm install -g llmxray
Check that it works
llmxray --help 2>&1The output should contain “Port to serve on”.
First thing to try
llmxray --port 5182 --observe-port 11436curl -s http://localhost:5182/ 2>&1Start the LLMxRay service, then open http://localhost:5182/ in your browser.
What it does
- Watch Ollama traffic through a live proxyNot tested
- Chat with local modelsNot tested
- Compare models side by sideNot tested
- Benchmark models using real logprobsNot tested
How far pickfit got
Linux x86_64
- Installs
- Starts
- 0 of 4 features work
- Works offline
Good for
- chat with a local model token by token
- compare the same prompt across models side by side
- benchmark models on curated question suites
- search PDF, DOCX, Markdown or CSV files via local retrieval
- observe cached tokens and model evictions
An alternative to Ollama.
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
Linux x86_64
Its service answers requests
- Replayed from scratch
- Works offline
- Checked on 30 Oct 2026
- Version 0.8.12