Fine-tune cheap open-source LLMs (GLM, Qwen, DeepSeek) on your AI coding agent's successful runs with LoRA (SFT + DPO) so your model cascade escalates to expensive frontier models (GPT, Claude) less often — cutting cost-per-resolved. Turns run history int

Custom metrics for AWS

Redis storage for NestJS Throttler enabling distributed rate limiting across multiple application instances

Simple breadth-first early terminating Levenshtein distance auto correcter for small sets of possible resulting strings.

Zero-dependency TypeScript parser for FIEBDC-3/BC3 construction budget files (Presto, ARQUIMEDES, TCQ). Builds a type-safe hierarchical model for bills of quantities, cost databases, and construction project budgets.

Rate limiting plugin for hapi

Find out which of your dependencies are slowing you down 🐢

Interactively manage concurrency for outbound requests.

Framework-agnostic rate limiting, budget tracking, and agent guard for AI gateways.

Node membrane library to create sandboxed environments in Node

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

A CLI tool to perform cost analysis on your AWS account

Common functionalities for the cost-insights plugin

CLI tool for Size Limit

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.

A Backstage plugin that helps you keep track of your cloud spend

A join-coefficients-fixed mediator

Tiny async queue with concurrency control. Like p-limit or fastq, but smaller and faster.

The Completion Node SDK is a fast and lightweight way to interact with the Completion API.

React hook for finding device pixel ratio (DPR), optionally capping/rounding