Offline BPE tokenizer for OpenAI, Anthropic, and Gemini — zero dependencies

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

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

A pure JavaScript implementation of a BPE tokenizer (Encoder/Decoder) for GPT-2 / GPT-3 / GPT-4 and other OpenAI models

tiktoken is a fast [BPE](https://en.wikipedia.org/wiki/Byte_pair_encoding) tokeniser for use with OpenAI's models.

WebAssembly bindings for bpe-openai tokenizer

Core runtime for counting BPE tokens.

BPE tokenizer used for the NovelAI frontend.

Estimate and count tokens (incl. exact OpenAI BPE) and input costs for LLM API calls

MCP server for the BPE (Bitcoin Pricing Engine) market-data API. Lets Claude Desktop, Cursor, and other MCP-enabled agents query consolidated BTC pricing, ML signals, funding-rate skew, and natural-language market briefings.

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

Fast tokenizer for language models, supporting BPE, Unigram and WordPiece tokenization

Javascript BPE Encoder Decoder for GPT-2 / GPT-3. The "gpt-3-encoder" module provides functions for encoding and decoding text using the Byte Pair Encoding (BPE) algorithm. It can be used to process text data for input into machine learning models, or to

Build your own vocabulary from application-specific corpus using Byte pair encoding (BPE) algorithm.

n8n node for working with BPE Tokens with OpenAI's GPT models in mind.

CLI tool to visualize Byte Pair Encoding (BPE) merge steps

A simple JavaScript implementation of Byte Pair Encoding (BPE)

BuilderForce Agent Memory — engine layer. TypeScript/WGSL Mamba SSM kernels, model blocks, autograd, training, and BPE tokenizer (zero runtime deps, WebGPU-native).

WASM bindings for the tiktoken BPE tokenizer

Javascript BPE Encoder Decoder for GPT-2 / GPT-3. The "gpt-3-encoder" module provides functions for encoding and decoding text using the Byte Pair Encoding (BPE) algorithm. It can be used to process text data for input into machine learning models, or to