[](https://github.com/rogeriochaves/llm-cost/actions/workflows/node.js.yml) [](https://www.npmjs.com/package/ll

SkillFM gateway MCP for LLM cost optimization, OpenAI/Anthropic usage, and Beacon audits.

OpenClaw plugin — Agent communication + LLM cost tracking + telemetry reporting

Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity receipts.

Unified observability, OpenTelemetry tracing, and LLM cost tracking for HazelJS agents and flows

TypeScript AI agent runtime control — enforce LLM cost limits, action permissions, and audit trails for agents before execution.

Official observability client for odla Cloudflare Workers — OpenTelemetry traces, metrics, structured errors, and LLM cost, exported over OTLP to the odla-o11y collector.

Official JavaScript/TypeScript SDK for LLMetrics — LLM cost & performance tracking

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

Server-side Node.js SDK for usage tracking, entitlement checks, margin intelligence, LLM cost capture, and billing management.

Pre-deploy LLM cost accident guardrail (serverless local CLI)

Enterprise-grade TypeScript SDK for LLM Cost Operations Platform

Enforceable, zero-LLM-cost repo self-documentation: an annotated directory tree with a cross-ecosystem dependency graph.

AI Margin Intelligence — one-line, fail-open OTel instrumentation that captures correct, per-attempt LLM cost for the OpenAI / Anthropic Node clients and the Vercel AI SDK.

SkillFM Beacon MCP: AI health checkups, token usage, LLM cost optimization, BYOK monitoring, and safe agent cleanup.

STAGING - LLM cost optimization plugin for Claude Code (internal testing)

LLM cost optimization plugin for Claude Code - Save up to 90% on AI costs

Runtime budget, action, and audit authority for OpenClaw agents — enforce LLM cost limits, tool call caps, and audit trails before execution.

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

MCP server exposing LLM cost telemetry as Model Context Protocol tools