@chonkiejs/chunk
The fastest semantic text chunking library
Found 189 results for tokenization
The fastest semantic text chunking library
Core chunking library for Chonkie - lightweight and efficient text chunking
Skyflow SDK for Node.js
Basis Theory utility for decrypting Apple Pay Tokens
Small, fast, event-driven, fault-tolerant html tokenizer. Works in node or browsers.
React components for accepting payments with HelloPay
Node.js bindings for BlingFire tokenization library
text segmentation into sentences
Waffo Payment SDK for secure card tokenization and iframe rendering
NLP (natural language processing) for server and the browser in TypeScript. All lightweight and super-fast.
A NLP library for Russian language
text segmentation into sentences
Easily create payment tokens using Flex API
Self-hosted AI context enforcement across LLM, MCP, vLLM, Ollama, and agent traffic — a stable, zero-dependency security gateway.
PCI-compliant card tokenization SDK for the Ozura Vault — collect card data in iframe-isolated fields and tokenize without PCI scope
Isomorphic utilities for GPT-3 tokenization and prompt building.
Wix Restaurants credit-cards tokenizer
Basis Theory utility for decrypting Google Pay Tokens
Privent DLP nodes for n8n: session-scoped tokenization, risk scoring, and safe detokenization for AI agent workflows
Official TypeScript SDK for Oumla - Blockchain integration made simple
A powerful and flexible text search library for JavaScript that enables you to build a simple text search engine.
Bedrock Tokenization Engine
Easily create keys for use in a Flex API integration and verifying Flex token contents
<div align="center">
Photon Enterprise SDK
Official AstroPay client for easy frontend integration to Tokenizer
FlintN Payment SDK — drop-in iframe checkout for card payments and wallets with localization and theming.
Reusable utility functions for REFE-style real-estate tokenization projects.
Official TypeScript SDK for the OpenCommodity™ protocol (operated by Railblock). REST client, typed events, ethers v6 contract wrappers, and v2 webhook verification.
Main NLPTools package - Complete suite of NLP algorithms, text distance, similarity, splitting, and tokenization utilities
Translucent iOS-style credit card input form and direct REST tokenization package for Stripe and Omise.
A parser and analyzer for advanced search queries, supporting tokenization, abstract syntax tree generation, and condition extraction.
A payment system module for SIBS payments integration with card tokenization support
AI agent runtime security: context-preserving tokenization, risk scoring, and policy enforcement
Tokenizing strings of text. Extracting arrays of words and optionally number, emojis, tags, usernames and email addresses from strings. For Node.js and the browser. When you need more than just [a-z] regular expressions.
A Stripe-like developer-friendly SDK for Amazon Payment Services integration. Supports payment links, hosted checkout, tokenization, webhooks, and payment management.
An LLM API proxy that detects and redacts PII, blocks sensitive content, and tokenizes fields — all before requests reach your AI provider.
NeoZip MCP server for ZIP archives, blockchain notarization, and AI agent integration (Beta)
Node.js / TypeScript client for the Subzero tokenization vault
NexusPay.js — PCI-compliant card tokenization and payment elements
English word and sentence tokenizer, for natural language processing.
A full-featured command-line ZIP application with NeoZipKit integration
A powerful, stateless, and pure TypeScript search engine for the Quran.
Regex-based syllable tokenization for Burmese and Myanmar-script ethnic languages (Karen, Mon, Shan). A JS/TS port of the ricelang Python package's syllable tokenizer.
TypeScript port of Sudachi morphological analyzer for Japanese text
A Bedrock module to provide auto-rotating tokenizers
API client for token processing by connecting to assca
CLI tool for the Agent Payment API
RWA Token SDK for the development of permissioned tokens on SVM blockchains.
MCP server for Izipay — Peru's enterprise acquirer (Niubiz). Card authorize/capture/refund, tokenization, cuotas, reconciliation.
OpenVINO™ Tokenizers adds text processing operations to openvino-node package
Independent TypeScript implementation of the SpreadsheetLLM SheetCompressor encoding for token-efficient LLM workflows.
Bonum payment SDK for Node.js - Gateway Merchant API (invoices, tokenization, subscriptions, QR) plus PSP Apple Pay / Google Pay
Natural language processing and text analysis
Secure payment tokenization SDK by Tokeflow
Single-file Node.js/TypeScript PII masking engine — detection + masking + tokenization, with streaming, Express middleware, risk scoring, and structure-aware (JSON/HTML/Markdown) helpers
Tokenization utilities - HuggingFace tokenizers wrapper for NLPTools
Babel Street Analytics API Node.js client SDK
MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,
DeFarm SDK - Git for traceability with multi-role permissions and global item discovery for agriculture supply chain
Cielo eCommerce nodes for n8n (tokenization, token payments, credential validation)
Bedrock VC Issuer Coordinator Storage
Nuvei Ecuador payment gateway adapter for Next.js: charge handler, webhook, 3DS flow, refunds, tokenized cards, and payment links. Part of panda-commerce-kit.
MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,
Bitbond Token Tool MCP — deploy and manage ERC20 tokens via AI agents
Deterministic, rule-based prose tokenizer for English and Markdown. High-precision splitting for paragraphs, sentences, and words with character-accurate offsets.
Textmate token-based language service for Visual Studio Code.
A high-performance wrapper around `Intl.Segmenter` for efficient text segmentation. This class resolves memory handling issues seen with large strings and can enhance performance by 50-500x. Only ~70 loc (with comments) and no dependencies.
A library for natural language processing tasks including tokenization, entity recognition, anonymization, semantic chunking, and much more.
TypeScript/Node.js 版 wordfreq,内置词频数据与中文分词词典,开箱即用的跨语言词频查询与 Zipf/分词能力。
TypeScript SDK for AddPay Cloud API - CNP payment processing
Enterprise-grade privacy utilities: PII detection, data masking, tokenization, and GDPR compliance. Part of the LanOnasis Security Suite.
High-performance library for tokenizing text.
JavaScript/TypeScript SDK for Blindfold Gateway
A powerful, lightweight TypeScript library for dynamic mathematical expression evaluation with support for variables, formulas, Unicode strings, and compiled expressions for high performance.
Taiwanese Hokkien Transliterator and Tokeniser
RWA Token SDK for the development of permissioned tokens on SVM blockchains.
Bedrock Tokenization Engine
React Native payment processing SDK for Tuna with native Apple Pay and Google Pay support
a wrapper around the LunaSec CLI enabling it to be used as an NPM package
TypeScript SDK for DeFi protocols on Mantle Network - Unified interface for swaps, lending, liquid staking, perpetual trading, cross-chain operations, Pyth oracles, token launchpad, and NFT minting
Library that allows you to make payments and tokenize debit and credit cards with Niubiz.
A Bedrock module to provide auto-rotating tokenizers
## How To Use
The fastest semantic text chunking library
A JSON parser implemented in TypeScript
Generic browser-safe ML primitives for tokenization, data cleaning, evaluation, simulation, scaling, and RL math.
An interface to the pruf network written in javascript
Salient is a natural language processing and sentiment analysis library
Official TypeScript SDK for the peyeeye PII redaction API — detect, redact, and rehydrate personal data in LLM pipelines with deterministic tokens, zero retention, and stateless sealed sessions.
Tools for manipulating sentences
n8n community node for Brickken API V2 - tokenization and STO operations on blockchain
[Future Scope - Do not use until v1.0.0] Basic NLP tools (tokenization, stemming, sentiment) for GlimLang
Tokenization Service's Smart Contracts
Use LLMs to run map-reduce summarization tasks on large documents until a target token size is met.
Fat Zebra payment processing library for Next.js and standalone environments
Professional SDK for tokenized assets and security tokens on blockchain
Official SDK for the Europa Tech real estate tokenization API
Compare and convert JSON to TOON format with token efficiency analysis – includes CLI, API, and Web UI server.
Official Node.js SDK for Portous Payment Platform - Accept payments, manage tokens, and handle transactions
A tokenizer and lemmatizer for canonical terms in text
ASON (Aliased Serialization Object Notation) - Token-optimized JSON compression for LLMs. Reduces tokens by 20-60% while maintaining perfect round-trip fidelity.
Here is a README generated from the code snippet:
Enterprise-grade AI Data Loss Prevention (DLP) SDK for TypeScript
Very fast Porter Stemmer implementation written in Javascript.
A simple iterative lexer written in TypeScript
LLM-powered enterprise treasury agent that deploys and administers tokenized equity and bonds on Hedera (testnet or mainnet) via the @hebx/hak-ats-plugin Hedera Agent Kit plugin.
Intelligent JSON compression for LLM API optimization
HRON (Hierarchical Reference Object Notation) is a structured text format focused on being readable, compact, and fast to parse.
🌌 FR3K NEXUS v2.0 - Advanced Quantum Trading Platform with AI Agents, Neural Interface, Cosmic Timing, and Mystical Analysis
n8n节点插件:基于jieba-wasm的中文分词功能
Kinetic Gain Embedded — drop-in audit-stream + Decision Card vault contract SDK for B2B SaaS. Emit hash-chained Suite-compliant audit events, enforce vault contracts before AI tools touch sensitive data, validate Decision Cards. TypeScript-first, dual ESM
A WebAssembly binding for the charabia multilingual text tokenizer used by Meilisearch.
Official Veilio SDK for JavaScript and TypeScript - Data tokenization and cyber-resilience API client
CLI for GOON (Greatly Optimized Object Notation) - Convert JSON to ultra-compact GOON format
A standalone, type-safe LLM SDK with multi-provider support, retry logic, context management, and intelligent tokenization.
SDK JavaScript para tokenização de cartões de crédito GOPAG API, mantendo conformidade PCI DSS Zoop
The most powerful AI-powered agent platform for Arbitrum. Build autonomous trading bots, DeFi yield optimizers, NFT agents, and smart contract deployers with GPT-4o intelligence. Features real-time analytics, halal-compliant mode, REST API, and Docker sup
#### Description I needed the SentenceSplitter from llamaindex but had to import the entire llamaindex package which is 1GB. I pulled it out and had GPT make a standalone version. It's not exactly the same but close.
Greatly Optimized Object Notation - Hyper-compact LLM-friendly data format
Basic English tokenizer
Client-side field encryption for Zoza Vault — X25519 ECDH + HKDF-SHA256 + AES-256-GCM. Tokens never hit your servers in plaintext.
Well typed, string transmutation via splicing, driven by definitions of regular expressions, priority match and recursive clauses
Bedrock Tokenized Cache
Prava SDK — PCI-compliant card enrollment for merchants
es6 version of aaditmshah/lexer
package to deploy the smart contracts that associate the tokens to the various clients proportional to their contribution
CLI tool to perform NLP on selected files
TypeScript-first PII detection & anonymization — 26 built-in detectors (email, SSN, IBAN, and more), 8 strategies (mask, redact, hash, AES-256 encrypt, tokenize, pseudonymize, generalize, synthesize), 6 compliance presets (GDPR, HIPAA, CCPA, PCI-DSS, SOX,
Framework for building standalone applications on top of the DeFarm platform
CyberSource 3DS Web SDK for browser-based integrations with Flex Microform support
Trusset SDK - End-to-end tokenization infrastructure for financial institutions
Tools for working with human language data.
Accithus Security SDK for 3DS authentication and card tokenization
Salient is a natural language processing and sentiment analysis library
Text decomposition: Compound → Molecule → Atom with sanitization (WASM)
Claude Code skill + MCP server for the Freedman Capital Group capital matching marketplace.
CLI for Blindfold PII detection and protection
POS tokenization of words int meaningful components usable in POS-Bayes & Elastic Search Indexes
Lendara Protocol SDK - Investment protocol on Stellar/Soroban using Trustless Work
Thin JavaScript SDK for collecting card payments via Paygenix. Wraps VGS Collect.js — merchants mount secure card fields and receive a tokn_xxx token without raw card data ever touching their server.
Zhex Elements — hosted card fields for PCI-safe tokenization. Mounts an iframe served by js.zhex.io and exchanges a Zhex token your server can charge.
MCP server implementation for XRP Ledger
Complete SDK for RWA (Real World Assets) tokenization, payments, subscriptions, and access control on Mantle Network
A command-line tool for managing VGS aliases for tokenization
DeonPay Elements SDK - Embeddable payment UI components with multi-acquirer routing
Librería de componentes React del design system de tokeniAr
Multi-criteria Cantonese segmentation with dashes, intermediates, pipes, and spaces.
MCP server for Blindfold PII detection - protect sensitive data in AI conversations
A comprehensive n8n community node for the Pendle yield tokenization protocol providing 20 resources and 200+ operations for DeFi yield trading, liquidity provision, and vePENDLE staking. Includes support for PT/YT token operations, market analytics, and
A TypeScript library for building powerful, composable parsers using the parser combinator pattern. Parsco provides small, reusable parsing tools that can be combined to create complex grammars and interpreters, all without separate tokenization or extern
Drop-in PII detection for logs and event payloads — 25 categories, zero runtime dependencies, runs in Node / browsers / Cloudflare Workers / Deno.
a lexer in javascript
Official TypeScript SDK for CapSign API
Break down text into array of words.
TypeScript SDK for the KeyStone OS settlement orchestration API
Node.js implementation of OpenAI's Harmony response format for structured conversational AI interactions
Jawi
A simple and efficient tokenizer for natural language processing tasks.
Photon Enterprise SDK
MCP server for RWA Kernel. Gives AI agents structured, tier-aware access to the registry of tokenized real-world assets (treasuries, MMFs, credit, compute, IP, carbon, energy, data, etc).
Official TypeScript/JavaScript SDK for DAPP AI Cost Platform
A compact, schema-driven, and token-optimal data format for LLM and Microservice communication.
Official JavaScript/TypeScript SDK for NeuralDLP - AI Privacy & Security Layer
TokenEX Node.js library for API
OpenZeppelin-style smart contract library for Real World Assets with configurable rules engine
AddrPass SDK — tokenized address sharing for JavaScript and TypeScript
Privacy Infrastructure for Enterprise AI — Official JavaScript/TypeScript SDK
A TypeScript/JavaScript Toolkit for Persian NLP
Adebiet
Text decomposition: Compound → Molecule → Atom with sanitization
tokenizing text by rules
TypeScript SDK for Prime Power Plant Tokenization Platform
Official SDK for MAS Hub - Enterprise blockchain platform built on MasChain
A reverse engineered Node.js client for the Blackbox.ai API, supporting chat completions with streaming and aggregated responses.
CleverTap ZeroPii SDK for Web - Tokenization SDK for PII data
Modular backend service for tokenization and smart contracts in real estate applications
Define a function to execute after completing token-defined tasks.
n8n node for Skyflow data privacy operations including detokenization
PIIvacy — PII scrubber for LLM calls. Three substitution modes (token, realistic, pass-through), pluggable patterns, BYO-LLM helpers, optional in-browser/local-model name redaction. Two functions, no proxy, no server.
Functions for filtering SQL-like json with conjunctive normal form filters
This template provides a minimal setup to get React working in Vite with HMR and some ESLint rules.
MCP library for AI-assisted Real World Asset tokenization on XRPL
a wrapper around the LunaSec CLI enabling it to be used as an NPM package
Provider-agnostic React Native card collection widgets (VGS, Skyflow, Basis Theory, Evervault + request-builder) behind one widget interface.
An Angular credit card input validation, tokenization, and payment processing widget component.
React Native SDK for secure card tokenization via Autra's hosted card page.