by tokentopapp · Agent Tool · ★ 51
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
htop for your AI costs — real-time terminal monitoring of LLM token usage and spending across providers and coding agents
| Stars | 51 |
| Forks | 5 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 38/100 |
| Open Issues | 13 |
| Last Updated | 2026-05-03 |
| Created | 2026-01-23 |
| Platforms | cli, node |
| Est. Tokens | ~1317k |
These tools work well together with tokentop for enhanced workflows:
Looking for a tokentop alternative? If you're comparing tokentop with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
🤖 AI assistant command and control dashboard — Spawn more Overlords!
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you co
htop for your Claude Code sessions — real-time cost, cache efficiency, model comparison, and smart alerts
Monitor all your coding agents from one terminal - Claude Code, Cursor, OpenCode, pi and more
10 Claude sessions running. What are they doing? Live dashboard — monitor, cost tracking, search, sub-agent vi
Explore other popular agent tool tools:
tokentop is htop for your AI costs — real-time terminal monitoring of LLM token usage and spending across providers and coding agents. It is categorized as a Agent Tool with 51 GitHub stars.
tokentop is primarily written in TypeScript. It covers topics such as ai, anthropic, bun.
You can find installation instructions and usage details in the tokentop GitHub repository at github.com/tokentopapp/tokentop. The project has 51 stars and 5 forks, indicating an active community.
tokentop is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to tokentop on Agent Skills Hub include toktrack, openclaw-command-center, Claude-code. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.