Show HN: PrismCat – Local transparent proxy and debugging console for LLM APIs
PrismCat is a self-hosted transparent proxy and debugging console designed for LLM APIs. It allows users to monitor and capture requests and responses between their applications and various LLM services. With features like full traffic observability and request replay, PrismCat aims to simplify debugging and enhance transparency in API interactions.
- ▪PrismCat enables users to see every request and response between their app and LLM APIs by changing a single line in the code.
- ▪It supports various LLM APIs, including OpenAI, Claude, and Gemini, and provides a user-friendly interface for monitoring traffic.
- ▪The tool is designed to run continuously, automatically capturing data without requiring manual intervention.
Opening excerpt (first ~120 words) tap to expand
🐱 PrismCat English | 简体中文 You never know how much junk your SDK silently injects into your prompts — until you use PrismCat. PrismCat is a self-hosted, transparent proxy and debugging console for LLM APIs. Change one line — your base_url — and instantly see every request and response between your app and OpenAI / Claude / Gemini / Ollama / any LLM API, including streaming (SSE). ⚡ Get Started in 30 Seconds 1. Launch Grab the binary for your system from Releases. Platform How to Start Windows Run prismcat.exe — it lives in your system tray Linux / macOS Run ./prismcat Docker See Docker Deployment Open http://localhost:8080 in your browser. 2. Add an Upstream In the Settings page, add an upstream.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.