Awesome AI Agents › Agent Monitoring Tools

MervinPraison/PraisonAI

⭐ 9051 Jupyter Notebook repository created 2024-03-19

PraisonAI is a production-ready Multi AI Agents framework designed to automate and solve problems ranging from simple tasks to complex challenges. It offers a low-code solution to build and manage multi-agent large language model (LLM) systems with an emphasis on simplicity, customization, and effective human-agent collaboration. The framework integrates PraisonAI Agents, AG2 (formerly AutoGen), and CrewAI to streamline multi-agent system development. Key features include automated AI agent creation, self-reflection, reasoning, multi-modal capabilities, multi-agent collaboration, workflow management, custom knowledge integration, short and long-term memory, chat with PDF agents, code interpreter agents, retrieval-augmented generation (RAG) agents, asynchronous and parallel processing, auto agents, math agents, structured output agents, LangChain integration, callback agents, mini AI agents, and over 100 custom tools. It supports YAML configuration and over 100 large language models. The framework is accessible via Python and JavaScript with simple code examples provided for single and multi-agent setups. It also offers a no-code auto mode for quick task execution. The project includes detailed documentation and visual diagrams illustrating AI agent workflows, tool usage, memory management, and different process types such as sequential, hierarchical, and workflow processes. PraisonAI is designed to facilitate the creation of intelligent AI agents capable of complex problem-solving and automation in a collaborative environment.

https://github.com/MervinPraison/PraisonAI

agentsaiai-agent-collaborationai-agent-frameworkai-agent-sdkai-agentsai-agents-frameworkai-agents-sdkai-automationai-framworkai-memoryai-workflowsaiagentaiagentframeworkaiagentsaiagentsframeworkasync-processingcallback-agentschat-with-pdfcode-interpretercustom-knowledge-integrationcustom-toolsframeworkjavascriptlangchain-integrationllm-supportlow-code-solutionmini-ai-agentsmulti-agentmulti-agent-collaborationmulti-agent-llm-systemsmulti-agent-systemmulti-agent-systemsmulti-agentsmulti-ai-agentmulti-ai-agentsmulti-modal-aipythonrag-agentsreasoning-aiself-reflection-aiyaml-configuration

Also in Agent Monitoring Tools

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.

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...

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.

ZHangZHengEric/Sage

Sage is a production-ready, modular multi-agent system framework that intelligently decomposes and orchestrates complex tasks using advanced AI models and provides an interactive web interface for real-time task visualization.