A lightweight large language model input-output tracker—launch with a single command, integrate effortlessly.
Overview
What is LLM-Tracker?
LLM-Tracker is a lightweight input-output tracker for large language models, designed to record interactions between applications and models during development.
How to use LLM-Tracker?
To use LLM-Tracker, compile the project using Go, and launch it with the command ./llm-tracker.exe --configFile=config.toml. Ensure you have the necessary configuration files in place.
Key features of LLM-Tracker?
- Hides the tools list in input to reduce clutter during interactions.
- Supports both streaming and non-streaming responses, allowing for efficient processing.
- Compatible with various modes including mcp/function_call/chat.
- Escapes special characters in input and output for better readability.
Use cases of LLM-Tracker?
- Tracking input-output interactions for large language models in real-time.
- Integrating with applications that utilize models like ollama and deepseek.
- Debugging and optimizing model interactions by analyzing recorded data.
FAQ from LLM-Tracker?
- What models does LLM-Tracker support?
LLM-Tracker currently supports models deployed with ollama, deepseek, and theoretically any model compatible with OpenAI SDK.
- How do I integrate LLM-Tracker with my application?
Change the IP and port in your workflow/client code to 127.0.0.1:1234 to connect to LLM-Tracker.
- Is LLM-Tracker free to use?
Yes! LLM-Tracker is open-source and available under the MIT license.