The fastest semantic text chunking library

Core chunking library for Chonkie - lightweight and efficient text chunking

Efficient, configurable text chunking utility for LLM vectorization. Returns rich chunk metadata.

Minimal recursive text chunking functionality extracted from @mastra/rag for edge deployments

Retrieval-pipeline utilities for @effect-uai/core: text chunking, rank fusion, and a Hugging Face tokenizer layer.

Local deterministic text chunking for memory and retrieval pipelines.

Professional TTS node with multi-engine support, text chunking, and accurate SRT generation

Token-aware, structure-aware text chunking for RAG - exact source offsets, sentence, markdown, code and HTML modes, pluggable tokenizer, zero dependencies.

MCP server for universal text extraction, keyword extraction, language detection, and text chunking for RAG pipelines

Token-aware text chunking for RAG pipelines — configurable overlap, sentence/paragraph-boundary awareness, and a pluggable tokenizer.

The fastest semantic text chunking library

An intelligent text chunking library that respects document structure and semantic boundaries

SHARC Splitter - AST and recursive text chunking for semantic search

Cloud-based chunkers for Chonkie - semantic, neural, and AI-powered text chunking via api.chonkie.ai

Smart text chunking for use in RAG systems

Fast JavaScript/TypeScript bundler in Rust with Rollup-compatible API.

A module for creating a node style stream over a WebExtension port object.

Split buffers and streams into smaller chunks

Boundary-aware text chunking with overlap for LLM/embedding pipelines — respects paragraphs and sentences, pluggable size metric.

Browser-friendly ChunkWise wrapper (Pyodide + WASM) for Arabic/English text chunking in the browser.