Local-first AI coding token usage and cost tracker for 29 tools, with a dashboard, desktop pet, widgets, achievements, and native macOS/Windows apps.

Local-first token API usage and cost tracker for AI coding agents on one machine

AI coding cost tracker — CLI + MCP server + REST API + web dashboard for Claude Code, Codex, Gemini, OpenCode, Cursor, Pi, and Hermes

Never lose your AI coding cost history — token & cost tracker for Claude Code, Codex, Gemini, Qwen Code, OpenCode & PI Agent, with a persistent cache that survives CLI data deletion.

Pi extension: AI coding cost tracker with widget, budget limits, and CNY pricing for Chinese models.

Core routing engine, cost tracker, and optimizer for AgentFare

LLM cost tracker — track spend per session, model, and project

Privacy-first, local-only LLM cost tracker. Track OpenAI, Anthropic, Gemini costs without sending data to the cloud.

Local-first Claude Code usage & cost tracker — OTLP + transcript ingest with a live dashboard.

Real-time token usage and cost tracker for Anthropic and OpenAI APIs

Local-first LLM cost tracker — no proxy, no cloud, no account. npm install is the entire infrastructure. Token attribution, optimization recommendations, and a 7-day local dashboard. OpenAI · Anthropic · Groq · Gemini · Ollama.

Claude Code Cost Tracker - Track token usage and costs for Claude Code sessions

Merged ecosystem plugins: conformance, cost-tracker, knowledge-workflow, lazy-loader, picker, semantic-cache, snapshot

AI cost tracker with hosted backend, CLI, and simple web dashboard.

Token usage and cost tracking for AI providers (OpenAI, Anthropic) with per-model pricing, usage reports, and budget alerts

Per-run / per-tenant USD aggregation: subscribes to model_response events, emits cost_accrual TraceEvents

🔬 Open-source Prompt Debugger for LLMs — token counter, cost tracker (₹/$), streaming, multi-provider (Groq, OpenAI, Together AI)

Real-time cost awareness for MCP agent workflows

Zero-dependency token usage and cost tracker for LLM APIs (Anthropic Claude, OpenAI, and any custom model). Track spend, cache savings, and budgets across requests.

Local-first LLM usage & cost tracker. Wrap your OpenAI/Anthropic/Gemini client in one line to measure tokens, cost, latency and per-feature spend — with a budget guard and a local dashboard. Zero exfiltration, zero runtime deps in the core.