Awesome AI AgentsAgent Monitoring Tools

agentscope-ai/agentscope-studio

⭐ 649 TypeScript repository created 2025-07-01

AgentScope Studio is the development-oriented companion application for the AgentScope agent framework. It runs locally as a Node.js service, installed globally from npm or started from source or Docker, and an AgentScope application connects to it by passing the studio URL into the framework initializer. Once connected, the studio records what the application does and presents it through a web interface. Projects and runs organise the history of executions, so a developer can group related experiments and return to an earlier run instead of re-reading raw logs. A chatbot-style runtime view shows agent interaction in real time and allows the developer to talk to the running application directly, which is useful while a conversational flow is still being shaped. Tracing is built on OpenTelemetry semantic conventions and visualizes LLM calls, token usage and nested agent and tool invocations, making it possible to see where latency and cost accumulate inside a multi-step run. An evaluation section analyses results from a statistical perspective rather than case by case, which suits benchmarking a change across many inputs. The studio also embeds a development assistant called Friday, which acts as a playground for rapid secondary development and as an integration point for the more advanced features. The frontend is TypeScript, the project is Apache 2.0 licensed, and documentation covers installation, project management, tracing conventions and the copilot. It is aimed at developers already building on AgentScope who need observability during development and debugging rather than a production monitoring stack, and it is one of the pieces of the broader AgentScope ecosystem maintained by the same organisation.

https://github.com/agentscope-ai/agentscope-studio

agentagentscopeobservabilitytracingopentelemetryllmmulti-agentdebuggingevaluation

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...

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.