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
jazzyalex/agent-sessions
Agent Sessions is a native macOS application, written in Swift and released under the MIT license, that reads the session history AI coding agents already write to local disk and turns it into a browsable, searchable archive. Supported sources listed by the project include Codex, Claude Code, OpenCode, Cursor Agent, GitHub Copilot CLI, Hermes, OpenClaw, Antigravity CLI, Pi, Kimi Code and Grok CLI, each stored in its own format such as JSONL files or SQLite databases. The app normalizes them into a single view with transcript inspection, image browsing, recovery of sessions the user thought were lost, and one-click resume commands for the CLIs that support resuming. Its distinguishing feature is quota attribution. A standard usage meter reports only an aggregate percentage, which is unhelpful when several agents run in parallel. Agent Sessions instead attributes consumption to the individual session and updates it live against the Codex and Claude five-hour and weekly windows. The user picks the lens they care about: the five-hour window, the weekly window, tokens per hour, or dollars. The dollar lens prices each model in a session at its own rate, so a session where an Opus orchestrator drives Sonnet subagents is costed per model rather than blended into a single average. An analytics view counts every enabled agent source rather than a fixed subset. The project also publishes Session-Bench, a comparison scoring how ten agent session formats fare against nineteen pass or fail criteria with supporting evidence. Operation is entirely local: no telemetry is collected and nothing is uploaded, with privacy and security notes in the repository. It requires macOS 14 or newer and is distributed as a signed DMG through GitHub releases. The audience is developers running several coding agents who need to see where their token budget went and to retrieve earlier work.
https://github.com/jazzyalex/agent-sessions
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.