token-counter 话题在 GitHub 上没有填写简介，这里按 Star 数汇总最相关的热门仓库。
Customize Claude Code's system prompts, create custom toolsets, input pattern highlighters, themes/thinking verbs/spinners, customize input box & user message styling, support AGENTS.md, unlock private/unreleased features, and much more. Supports both native/npm installs on all platforms.
Intercept LLM API traffic and visualize token usage in a real-time terminal dashboard. Track costs, debug prompts, and monitor context window usage across your AI development sessions.
用于 Claude CLI 的 macOS 菜单栏仪表板，显示 token 用量、预估成本以及按模型 / MCP / Skill 的细分统计
📐 Fast token estimation with 95%+ average accuracy in a 2kB bundle
Deep analytics and session insights for your Claude Code usage
Self-hosted browser tool for counting and inspecting text tokens, with a Chinese UI adapted from the OpenAI Tokenizer.
Lightweight, dependency-free logging and analytics for LLM API calls — track tokens, cost, and latency to a plain JSONL file.
AI编码代理（Claude Code、Cursor、Codex）与模型API（Anthropic、OpenAI、Gemini、MiniMax）之间的本地流式反向代理。它衡量每个代币+美元的成本，压缩臃肿的上下文以削减按代币付费的API支出，并运行影子评估以证明质量被持有。CCusage风格的计量+实时本地仪表盘。
Scalable LLM cost enforcement middleware for Node.js with budget protection and multi-provider support
Tiny native Windows session stats inside Codex: token totals, cache hits, native context usage, and output speed. About 11 MB helper memory; no Node.js/Python runtime.
Zero-config CLI for analyzing AI model usage & costs across all local TUI tools — pi, Claude Code, Codex, Gemini CLI, OpenCode, and more
Track LLM token usage, enforce rate limit & budget policies, and trigger alerts across OpenAI, Groq, OpenRouter, and AWS Bedrock.
A Chrome extension that tracks your daily ChatGPT token usage with a live progress bar, model detection, and plan-aware limits.
Open-source context engineering for AI coding: context budget, Claude Code, GitHub Copilot and Codex usage in tokens or API-equivalent cost, tab relevance, current model pricing, code maps, and workspace security.
🐳 鲸鱼电表：你在 DeepSeek Harness 上烧了多少 token？消耗量段位、可晒的战绩卡、6 家厂商 46 个模型精准计价（含国内分档）、8·17 调价前后对比。零配置，数据全在本机 | Token usage tiers & cost dashboard for DSH
Free LLM token counter: see how GPT-4 and GPT-4o split your prompt into tokens, which lines cost the most, and which wordy phrases to cut, with savings measured by re-tokenizing. Windows .exe, macOS, Linux. Uses tiktoken.
「DSH·实时 token 统计」：基于 DeepSeek 官方 BPE 分词表，在输入框下方实时渲染 token 状态带，显示流式 TPS、输出 token 与首字延迟。
A token counter answers two questions before you send a request: does the prompt fit, and what will it cost. How counting works and where estimates go wrong.
Inspect Claude Code / Codex CLI conversations locally. Token breakdown, per-turn costs, compaction timeline, framework-overhead audit. Python + tiktoken.
Local Tokenizer/Counter