token-tracker Alternatives

Token Tracker is a free, open-source, local-first dashboard for tracking token usage in AI coding agent CLIs. It gathers token counts in one place across 13 tools, giving a single view of model and project usage while recording only token counts rather than prompts or conversation content. After installation with npx tokentracker-cli, the CLI auto-detects installed AI coding tools, adds the appropriate hooks or log readers, and opens a local dashboard at http://localhost:7680. Supported tools include Claude Code, Codex CLI, Cursor IDE, Gemini CLI, OpenCode, OpenClaw, Every Code, Kiro, Hermes Agent, GitHub Copilot, Kimi Code, oh-my-pi (omp), and CodeBuddy. The dashboard runs on the user's machine and does not require an account. Cloud sync is optional and is used only for the public leaderboard. The local app presents a unified usage dashboard with input, output, cached, and cache-creation tokens across all 13 tools. It also includes per-model cost analysis across 70+ models, a usage-limits view with live rate-limit and subscription status for Claude, Codex, Cursor, Gemini, Kiro, and Antigravity, project attribution, activity heatmaps and trend charts, a skills browser, and a macOS menu bar app plus desktop widget for at-a-glance viewing. Token Tracker normalizes nine distinct log formats into a unified schema and serves aggregated bucketed counts from a local HTTP API on port 7680. It is built for developers, founders, and engineering teams that rely on multiple AI coding assistants and need a single place to understand token consumption. The project is described as open source, with source on GitHub and an npm package named tokentracker-cli.

cctrack-ai is an open-source command-line tool that enables developers to track and analyze AI token usage from Claude Code and other CLI agents. It provides structured analytics to help manage costs and optimize AI workflows.

toktrail is an open-source CLI tool that helps developers track, import, and analyze billable token usage from various AI harnesses and models. It stores session data in local SQLite, provides cost breakdowns by harness, model, and agent, and supports importing events from tools like OpenCode, Copilot CLI, and Claude. Ideal for developers managing AI usage and costs.

cctrack is an open-source CLI tool for developers to analyze Claude Code JSONL logs, reporting token usage and estimating associated costs. It helps teams monitor and optimize their AI API usage efficiently.

tokenol is an open-source CLI tool for auditing Claude Code JSONL session logs. It tracks cost, cache health, and context usage, helping developers monitor and optimize their LLM workflows.

harness-token-trace is a Python package that decomposes token usage and associated costs on a per-API-call basis. It is designed specifically for developers working with Claude Code, Claude desktop agents, and the Cursor AI code editor. The tool provides detailed observability into LLM token consumption and spend to help track and optimize costs.

tokenpayback is a command-line tool that reads local sessions from various AI coding agents and provides detailed reports on token usage and ROI. It helps AI developers and engineering teams monitor and optimize their agent workflows.

tokmeter is an open-source local dashboard and CLI tool that allows developers to track and analyze token usage and costs for Claude Code and Codex APIs. It runs locally and supports multiple operating systems.

local-ai-track is an open-source CLI tool that allows developers to monitor and track AI token usage and associated costs for coding assistants directly on their local machine. It is designed for developers who want privacy and transparency in their AI tool usage.

Local-first, read-only AI coding agent token and usage inspector.

codex-usage-tracking is an open-source CLI tool and dashboard for developers to investigate aggregate token usage, costs, caching, and thread patterns when working with OpenAI Codex APIs. It helps users monitor and optimize their API consumption and spending.