LLM Usage, Cost and Performance Monitoring - Backend API

Track LLM usage and costs with minimal setup

Policy & governance for AI & LLM usage

OpenCode plugin — LLM subscription limits + API spend tracking via llm-usage-tracker backend

OpenClaw plugin that reports per-call LLM usage from runtime hooks to the Velanir platform.

DeepClaw observability plugin for OpenClaw — real-time LLM usage, token, cache, reasoning, and cost telemetry.

Corelay Mesh Agent — zero-dependency telemetry SDK. Reports health, errors, LLM usage, and HTTP metrics to Corelay Command.

TypeScript SDK for fin — track LLM usage events

Local, read-only web dashboard for llm-logs. Point it at your DB; inspect your LLM usage.

CLI tool for packing files into a prompt for LLM usage.

CLI tool to tokenize codebases for LLM usage

OTEL-based observability for any Node.js service — standalone, no dependency on @svantic/sdk. Provides W3C-compliant tracing, LLM usage tracking, and context propagation with pluggable auth and export.

Detox driver for Wix Pilot usage

LLM eval & testing toolkit

Local desktop dashboard for Codex (OpenAI) and Claude Code subscription usage, limits and cost

[](https://dl.circleci.com/status-badge/redirect/gh/taneliang/coerce-llm-output/tree/main) [![codecov](https://codecov.io/github/taneliang/coerce-l

LLM integration plugin for PostGraphile v5 — server-side text-to-vector embedding and text companion fields for pgvector columns

Display language model outputs in your React project.

Estimate the electricity, CO2 and water footprint of your LLM usage across coding agents (Claude Code, OpenCode, Codex CLI)

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.