A pure JavaScript BPE tokenizer with model metadata and pricing for GPT-5, GPT-4o, o-series, and other OpenAI models

Provides a way to share files directly with other compatible applications.

Core types and registry utilities for TokenLens (model metadata).

Helpers for context windows, usage normalization, compaction, and cost estimation.

Front-end utilities for Nextcloud files sharing

Synchronous shared context compression with node's native zlib

Utilities for managing the current execution context

The **Model Context Protocol (MCP) client** for the [AI SDK](https://ai-sdk.dev/docs) lets you connect to MCP servers and use their tools with AI SDK functions like `generateText` and `streamText`.

The world's strongest free coding agent

Calculate the token consumption and amount of openai gpt message

The logging package for the Powertools for AWS Lambda (TypeScript) library

Simple, independently audited, zero-dependency TypeScript implementation of Shamir's Secret Sharing algorithm

Core logic for Polaris Viz that is not platform specific

Pi provider package for CLIProxyAPI with automatic model discovery and models.dev enrichment.

React way perf context selector

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

React useContextSelector hook in userland

This is an internal utility, not intended for public usage.

Javascript BPE Encoder Decoder for GPT-2 / GPT-3

Simple to use, blazing fast and thoroughly tested websocket client and server for Node.js