LLM Tracker FAQs

Question 1

Is LLM Tracker difficult to set up?

Accepted Answer

No, setup is relatively straightforward. You compile the project, configure the config.toml and rules.toml files, and then run the executable. Detailed instructions are available in the project's README.

Question 2

What is LLM Tracker?

Accepted Answer

LLM Tracker is a tool designed to monitor and track input and output interactions between your applications and large language models. It provides insights into the communication, helping you debug and optimize your AI applications.

Question 3

What kind of information does LLM Tracker capture?

Accepted Answer

LLM Tracker captures both the input and output data exchanged between your application and the large language model, including support for both streaming and non-streaming responses. It also masks tools lists to reduce noise and escapes special characters for readability.

Question 4

Which LLMs does LLM Tracker support?

Accepted Answer

LLM Tracker currently supports models accessible via the OpenAI SDK, Ollama, and Deepseek. It is compatible with MCP, function_call, and chat modes.

Question 5

How do I integrate LLM Tracker with my application?

Accepted Answer

Simply redirect your application's large language model requests to LLM Tracker's proxy by changing the IP and port to 127.0.0.1:1234.

LLM Tracker

About

Key Features

Use Cases