#26 · Primary category: MLOps & Evaluation
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
Project last updated:02/11/26
GitHub Stars
16.2K
Forks
3.6K
Contributors
28
License
Apache-2.0
Why we included this project
Debugging a multi-agent system usually means staring at logs and guessing which step produced the bad output. RagaAI Catalyst is a Python SDK that traces the agent's steps, including the LLM calls and tool interactions behind them, then shows the results in a self-hosted dashboard with timeline and execution-graph views, so you can see where a run went wrong instead of inferring it. It also bundles evaluation tooling: define datasets, attach metrics like faithfulness and hallucination with configurable thresholds, and run experiments to compare versions. Prompt management, synthetic data generation, guardrails, and red-teaming round out the package, so the same toolchain covers both debugging a single run and ongoing quality checks. Teams building RAG pipelines or multi-agent systems who want tracing and evaluation without stitching several services together will find most of what they need here.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
unsloth
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, FLUX and more.
LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
airflow
Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
langfuse
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
netron
Visualizer for neural network, deep learning and machine learning models