# raga-ai-hub/RagaAI-Catalyst

Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced analytics with timeline and execution graph view

Repository: https://github.com/raga-ai-hub/RagaAI-Catalyst
Canonical: https://ross.abutalabs.com/products/ragaai-catalyst
Homepage: https://catalyst.raga.ai/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agentneo, agents, ai-performance-optimization, llm-testing, llmops, agentic-ai-development, ai-agent-monitoring, ai-application-debugging, ai-evaluation-tools, ai-tool-interaction-monitoring, llm-tracing, agentic-ai
Last push: 2026-02-11T14:43:33+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 67, release rhythm 40, longevity 52
- inputs: {"age_days": 737, "days_push": 203, "days_rel": 436, "gap_med": 13.5, "n_releases_24m": 17}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 16150, forks 3567 (observed 2026-08-28T04:11:14.857497+00:00)

## What it is
RagaAI Catalyst is a Python SDK for observability, monitoring, and evaluation of LLM and agentic AI applications, with tracing of agents, LLMs, and tool calls. It includes a self-hosted dashboard with timeline and execution graph views, plus dataset, prompt, guardrail, and red-teaming management.

## Use cases
- trace and debug multi-agent LLM systems
- monitor LLM application performance in production
- evaluate LLM outputs against datasets
- manage and version prompts for LLM apps
- generate synthetic test data for LLM evaluation
- add guardrails and run red-teaming on AI agents
- visualize agent execution graphs and timelines

## When to choose
- you are building LLM or multi-agent applications and need tracing and debugging
- you want a self-hosted observability dashboard for AI agents
- you need evaluation, guardrails, and red-teaming in one SDK

## When to avoid
- you only need simple logging without LLM-specific analytics
- your stack is not Python-based
- you want a fully managed SaaS-only solution with no self-hosting

## Facets
- artifact type: library
- maturity: active
- function: monitoring, tracing, llm-inference, agent-framework, testing, analytics, data-visualization, sdk
- domain: large-language-models, machine-learning, developer-tools, monitoring
- platform: python, self-hosted
- tags: llm-observability, agent-tracing, llm-evaluation, llmops, guardrails, prompt-management, red-teaming, synthetic-data, ai-agents, web-server

## Member repositories
- raga-ai-hub/RagaAI-Catalyst (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:14.857497+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:05:13.160813+00:00, confidence not recorded.
  - readme: https://github.com/raga-ai-hub/RagaAI-Catalyst (fetched 2026-08-28T04:11:14.857497+00:00, sha 9ff9e298564f)
- Data as of 2026-08-30T08:39:29.467469+00:00.