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
l3vels/team-of-ai-agents
L3AGI (Team of AI Agents) is an open-source framework designed to enable AI assistants to collaborate as effectively as human teams. It provides a comprehensive platform for creating, managing, and executing autonomous AI assistants and teams of assistants that work together on complex tasks and simulations. The framework emphasizes team collaboration among AI agents, allowing them to share information, coordinate actions, and leverage collective intelligence to achieve goals more efficiently. Key features of L3AGI include the ability to design autonomous AI assistants with memory capabilities, enabling them to retain and recall information for better decision-making. The framework supports integration with various data sources such as Postgres, MySQL, files, web pages, Notion, Google Analytics, and Firebase, enhancing the assistants' access to diverse information. It also incorporates advanced data management tools like VectorDBs and LlamaIndex (GPT Index) to improve data querying and retrieval. L3AGI offers a rich set of toolkits tailored for specific tasks, including search engine result pages (SERP), web scraping, DuckDuckGo, Bing, Wikipedia, Arxiv, OpenWeather, charts, Twilio, Twitter, Instagram, Slack, Gmail, and Google Calendar. These tools empower AI assistants to perform a wide range of functions, from data gathering to communication and scheduling. The framework includes a user-friendly React-based UI for building and managing AI assistants and their teams, along with robust APIs for seamless integration and customization. It supports community engagement for collaborative development and improvement of AI assistants. The project provides detailed documentation, quick start guides, and a roadmap for future enhancements. Overall, L3AGI aims to push the boundaries of AI collaboration by creating a scalable, extensible environment where multiple AI agents can work together effectively, mimicking human team dynamics to solve complex problems and automate workflows.
https://github.com/l3vels/team-of-ai-agents
Also in Agent Monitoring Tools
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.
FailproofAI/failproofai
Local observability and policy-enforcement layer that hooks into 12 AI agent harnesses, including Claude Code, Codex and Hermes, to log every run and block dangerous tool calls before they execute.
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.
traceroot-ai/traceroot
TraceRoot is open-source observability for AI agents that traces runs, detects failures with LLM judges, root-causes them against source code and GitHub history, opens fix PRs and evaluates each fix.