Home

Decision-level observability for ML/LLM pipelines.

X-Ray captures why decisions were made—candidates considered, filters applied, scores computed, and reasoning behind each step—not just what functions ran.

Getting Started

Quick Start Guide - Get running in 5 minutes

Documentation

Page	Description
Quick Start	Installation and first pipeline
Architecture	System design, data flow, and internals
API Reference	Complete endpoint documentation

Quick Links

• GitHub Repository
• PyPI Package
• Docker Image
• Examples

Key Features

• Decision Transparency - Capture candidates, scores, and reasoning
• Lightweight SDK - Simple decorators, fail-open design
• FastAPI Middleware - Automatic HTTP instrumentation
• PostgreSQL/SQLite - Flexible storage options
• Query API - Filter and analyze pipeline runs