Monitor how many tokens your code and configs consume in AI tools. Set budgets and get alerts when limits are hit

Information on LLM models, context window token limit, output token limit, pricing and more

9 premium multi-select tag-input variants: default, avatar, grouped, creatable, colors, token limit, async search, inline and overflow.

OpenCode TUI plugin that shows Zhipu (智谱/GLM/Z.ai/BigModel) quota usage — 5h token limit, monthly MCP limit, 24h token total, per-model and per-tool breakdown — in the sidebar.

MCP server that gives Claude Code persistent memory of your codebase, backed by Gemini's 2M-token context. Includes eager `ask`/`code` for cached repo Q&A and `ask_agentic` for agentic file access on repos that exceed the model's input-token limit.

Your token limit just reset and you've got 37% to burn before it expires. Use every last one — gloriously.

Run multiple promise-returning & async functions with limited concurrency

Basic IP rate-limiting middleware for Express. Use to limit repeated requests to public APIs and/or endpoints such as password reset.

Converts SVG file to utf-8 encoded data-uri string

High Performance In-Memory Cache for Node.js

Call an array of promise-returning functions, restricting concurrency to a specified limit.

A rate limiter component for Convex. Define and use application-layer rate limits. Type-safe, transactional, fair, safe, and configurable sharding to scale.

File size plugin for Size Limit

Run an array of functions in parallel, but limit the number of tasks executing at the same time

A Redis store for the `express-rate-limit` middleware

CLI tool for Size Limit

limits calls to functions that return promises

A fast function for calculating where a string should be truncated, given an optional width limit and an ellipsis string.

This package is a helper to run multiple promise-returning & async functions with limited concurrency.

A low overhead rate limiter for your routes