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
ZHangZHengEric/Sage
Sage is a sophisticated multi-agent system framework designed to simplify the execution of complex tasks by intelligently decomposing them into manageable subtasks. It features seamless collaboration among specialized agents, robust error handling, and a modular plugin-based architecture that supports extensibility through MCP servers and auto-discovery of tools. The framework offers two distinct execution modes: Deep Research Mode for comprehensive, in-depth analysis and Rapid Execution Mode for faster task completion, catering to different user needs. The system includes an interactive web interface built with React and FastAPI, providing real-time streaming visualization of agent activities and task progress. Sage supports advanced token tracking for detailed usage statistics and cost monitoring across all agents, ensuring efficient resource management. It is developer-friendly, offering clean APIs, extensive documentation, examples, and strong error handling mechanisms, making it suitable for production environments with features like robust error recovery, logging, retry mechanisms, and performance optimization. Sage supports a variety of advanced language models such as DeepSeek-V3, Qwen-3, GPT-4.1, and Claude-3.5 Sonnet, integrating with multiple AI providers including OpenAI, OpenRouter, Anthropic, Google AI, DeepSeek, Alibaba Cloud, and Mistral AI. This compatibility ensures flexibility and broad applicability across different AI-driven tasks. The architecture of Sage involves a series of agents responsible for task analysis, decomposition, planning, execution, observation, and summarization, all coordinated to achieve efficient problem-solving. The tool ecosystem within Sage manages both local and remote tools, integrating external APIs and providing comprehensive results back to the observation agent. The framework is easy to install with automated scripts and supports a modern web application for interactive use. Overall, Sage is a production-ready, intelligent multi-agent orchestration framework that empowers users to tackle complex problems through modular design, advanced AI integration, and user-friendly interfaces.
https://github.com/ZHangZHengEric/Sage
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.