---
name: "Evaluate and trace agent workflows with RagaAI Catalyst"
slug: "evaluate-and-trace-agent-workflows-with-ragaai-catalyst"
description: "Use RagaAI Catalyst to instrument agent runs, collect traces, manage evaluation datasets, inspect execution graphs, and review regressions before deployment."
github_stars: 16167
verification: "security_reviewed"
source: "https://github.com/raga-ai-hub/RagaAI-Catalyst"
author: "raga-ai-hub"
publisher_type: "open_source"
category: "Monitoring & Alerts"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "raga-ai-hub/RagaAI-Catalyst"
  github_stars: 16167
---

# Evaluate and trace agent workflows with RagaAI Catalyst

Use RagaAI Catalyst to instrument agent runs, collect traces, manage evaluation datasets, inspect execution graphs, and review regressions before deployment.

## Prerequisites

Python environment, ragaai-catalyst SDK, Catalyst project credentials, instrumented LLM or agent workflow, and evaluation datasets or trace samples.

## Installation

Use the upstream install or setup path that matches your environment:
- To install RagaAI Catalyst, you can use pip:
- pip install ragaai-catalyst

Requirements and caveats from upstream:
- python

Basic usage or getting-started notes:
- [Usage](#usage)
- Before using RagaAI Catalyst, you need to set up your credentials. You can do this by setting environment variables or passing them directly to the RagaAICatalyst class:
- from ragaai_catalyst import RagaAICatalyst

- Source: https://github.com/raga-ai-hub/RagaAI-Catalyst
- Extracted from upstream docs: https://raw.githubusercontent.com/raga-ai-hub/RagaAI-Catalyst/HEAD/README.md

## Documentation

- https://catalyst.raga.ai/

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/evaluate-and-trace-agent-workflows-with-ragaai-catalyst/)