#16 · Primary category： AI Usage & Cost Monitoring
Claude-Code-Agent-Monitor
Real-time monitoring dashboard for Claude Code and Codex agent sessions, tool usage, and subagent orchestration with live analytics and a Kanban board.
Project last updated：08/29/26
GitHub Stars
956
Forks
221
Contributors
28
License
MIT
Why we included this project
Anyone who has run Claude Code or Codex across a few machines knows how little visibility there is into what the agents are doing. This dashboard collects session records, tool calls, agent activity, and subagent orchestration through the agents' native hook systems, then pushes everything to a React UI over WebSockets. It also lays the work out on a Kanban board, estimates token and cost per model, and lets you start new sessions from the interface, with macOS and Windows desktop apps as an alternative to the browser. Because it is local-first and stores data in SQLite, you get that visibility without sending telemetry to a third party.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
CodexBar
Show usage stats for OpenAI Codex and Claude Code, without having to login.
codeburn
Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn
Claude-Code-Usage-Monitor
Real-time Claude Code usage monitor with predictions and warnings
helicone
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
agentsview
Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 20 other agents.