raga-ai-hub/RagaAI-Catalyst
RagaAI Catalyst is a Python SDK platform for observability, monitoring, and evaluation of AI agents and LLM projects, featuring tracing, debugging, advanced analytics, and project management tools.
Awesome AI Agents › Agent Monitoring Tools
Azure-Samples/azure-ai-travel-agents
The Azure AI Travel Agents project is a comprehensive enterprise application designed to enhance travel agency operations through the use of multiple AI agents. Hosted on Azure Container Apps (ACA), the application leverages the Model Context Protocol (MCP) and LlamaIndex.TS to orchestrate various AI agents that assist in handling customer queries, providing destination recommendations, and planning detailed itineraries. The system is modular and scalable, with components containerized using Docker for easy deployment and management. The application features several specialized AI agents, including Customer Query Understanding, Destination Recommendation, Itinerary Planning, Code Evaluation, Model Inference, Web Search, and Echo Ping. These agents work collaboratively, each serving a distinct purpose such as extracting customer preferences, suggesting travel destinations, creating travel plans, executing custom logic, running custom large language models (LLMs) using ONNX and vLLM on serverless GPU infrastructure, and fetching live travel data via Bing Search. The architecture supports multiple programming languages and frameworks, with MCP servers implemented in Python, Node.js, Java, and .NET, demonstrating interoperability and flexibility. The Agent Workflow Service orchestrates interactions between agents and MCP clients, ensuring seamless cooperation. Additionally, the Aspire Dashboard provides monitoring capabilities with OpenTelemetry integration, offering insights into agent performance and behavior. The project supports local preview and testing through Docker Model Runner, although running the Phi4 14B model requires significant hardware resources. For users without sufficient local resources, the application can be run using Azure AI Foundry. The repository includes setup scripts to automate environment configuration, dependency installation, and model downloading. Overall, Azure AI Travel Agents showcases advanced AI orchestration in a real-world travel agency context, combining multiple AI technologies and cloud-native deployment strategies to deliver a powerful, scalable solution for travel planning and customer service enhancement.
https://github.com/Azure-Samples/azure-ai-travel-agents
Also in Agent Monitoring Tools
superset-sh/superset
Superset is a desktop application (macOS) designed to orchestrate and manage multiple CLI-based AI coding agents in parallel using isolated Git worktrees, featuring built-in diff viewing and IDE in...
MervinPraison/PraisonAI
PraisonAI is a production-ready Multi AI Agents framework that enables the creation and management of intelligent AI agents to automate and solve complex problems through collaboration and customization.
apache/hertzbeat
Apache HertzBeat is an AI-powered open source real-time observability system that unifies metrics and logs collection, alerting, and notification with high performance and customizable monitoring capabilities.
junhoyeo/tokscale
Tokscale is a CLI utility and dashboard for tracking and visualizing token usage and costs across various AI coding agents.
matt1398/claude-devtools
Desktop and Docker application that reads local Claude Code session logs and reconstructs tool calls, thinking steps, subagent trees and per-turn token attribution in a visual interface.
eumemic/ai-legion
AI Legion is a platform for autonomous agents powered by large language models that collaborate to accomplish tasks with minimal human intervention.
chiphuyen/sniffly
Sniffly is a local analytics dashboard that parses Claude Code logs to show usage statistics, error breakdowns and full message history, with optional shareable dashboards.