Know exactly what every database read costs you — and who caused it. A tiny, never-throws read-cost collector for Firestore, MongoDB & Postgres — server and browser.
Token usage tracker for AI agent CLIs (Claude Code, Codex, Cursor, Gemini, Antigravity, Kiro, OpenCode, OpenClaw, Every Code, Hermes, GitHub Copilot, Kimi Code, CodeBuddy, WorkBuddy, Grok Build, oh-my-pi, pi, Craft Agents, Kilo CLI, Kilo Code, Roo Code, Z
Track model usage, tokens, and costs per agent in the OpenCode TUI sidebar
Cost-aware delegation enforcer for OpenCode. Tracks model usage, routes Task subagents to cheaper tiers, surfaces cumulative savings in chat. Includes research audit, reporting framework, project memory, progressive scratchpad decadence, and trinity CLI f
AI model catalogs (open-assets JSON), cost calculation, and LLM utilities
Cost calculator for Vercel AI SDK token usage. Supports OpenAI, Anthropic, Google, xAI (Grok), and DeepSeek with long context pricing, prompt caching, and reasoning tokens.
Gold-standard OpenTelemetry GenAI semantic-convention instrumentation for LLM calls, tools, and agents — cost, tokens, metrics, events, and agent governance.
Usage statistics footer widget for Pi sessions.
Per-user AI cost tracking and rate limiting for indie developers
OpenCode TUI sidebar: precise prompt-cache, token, cost, context, tools, skills, speed & sub-agent usage. English/USD only.
AI inference optimization — smart routing + context compression saves up to 98% on LLM costs
SuperBased Observer — capture, normalize, compress, and analyze AI coding tool activity across Claude Code, Codex, Cursor, Cline/Roo, and Copilot.
See where your coding-agent tokens go. One local command — Codex, Claude Code, Qwen Code, OpenCode & more. Zero upload.
MCP server para consultar dados de FinOps do CloudBroker (custo, forecast, IA, recomendações, anomalias) via assistente de IA.
Golden datasets, scorecards, and cost-quality evaluation contracts for Plasius AI workloads.
Wrap your OpenAI, Vercel AI SDK, Mastra, LangChain, or OpenAI Agents calls to track token usage and cost. Never touches keys, prompts, or completions.
Official JS client for the Arbr AI control-plane gateway — one function to route, observe, and govern every LLM call.
Local-first, FOCUS-native cost and limit visibility for your AI coding tools, right in your terminal.