abtop: a TUI monitoring dashboard for tracking token usage and resource consumption across multiple AI coding agent sessions

What it solves

abtop provides a centralized monitoring dashboard for users running multiple AI coding agents simultaneously. It solves the problem of tracking token usage, context window saturation, rate limits, and orphaned processes across different agent sessions (such as Claude Code, Codex CLI, and OpenCode) without having to switch between multiple terminal windows.

How it works

It operates as a read-only TUI (Terminal User Interface) that discovers active agent sessions by scanning local process and file states. It monitors system metrics via sysinfo and detects listening ports using netstat. For specific agents like OpenCode, it reads local SQLite databases. It does not require API keys or authentication, as it derives its data from local metadata and transcripts.

Who it’s for

Developers who use AI coding agents across multiple projects and need a real-time overview of their resource consumption, quota status, and background processes.

Highlights

• Multi-Agent Support: Monitors Claude Code, Codex CLI, and OpenCode in one screen.
• Resource Tracking: Real-time visibility into token usage, context window percentages, and rate limits.
• Process Management: Detects orphan ports and allows users to kill selected sessions or all orphan ports directly from the TUI.
• Terminal Integration: Supports jumping directly to the terminal pane running a selected agent via cmux, tmux, or iTerm2.
• Crate Library: Includes a library crate and JSON snapshot export for building custom dashboards or scripts.