npmjs.org "chunking" keyword
chunklet 0.2.0
Token-aware, structure-aware text chunking for RAG - exact source offsets, sentence, markdown, co...3 versions - Latest release: about 1 month ago - 288 downloads last month - 0 stars on GitHub - 1 maintainer
turnchunk 0.4.1
Chunking that understands who is speaking. Parse any transcript, chunk it without ever splitting ...5 versions - Latest release: about 2 months ago - 282 downloads last month - 6 stars on GitHub - 1 maintainer
ngx-fastboot 2.1.0
ngx-fastboot is an Angular library designed to dynamically load configuration settings at runtime...9 versions - Latest release: over 1 year ago - 367 downloads last month - 8 stars on GitHub - 1 maintainer
chunk-lite 0.1.0
Token-aware text chunking for RAG pipelines — configurable overlap, sentence/paragraph-boundary a...1 version - Latest release: about 2 months ago - 1 maintainer
rag-toolkit 1.1.0 💰
Tiny RAG toolkit — chunking, embeddings abstraction, metadata, similarity search, and context bui...3 versions - Latest release: about 2 months ago - 0 stars on GitHub - 1 maintainer
@cocreate/webpack 1.11.0 💰
A Webpack integration tool for CoCreate applications, enabling file watching, automated chunking,...22 versions - Latest release: about 5 hours ago - 112 downloads last month - 0 stars on GitHub - 1 maintainer
semantic-chunker 0.0.4
A tool for semantic chunking of text5 versions - Latest release: 3 months ago - 29 downloads last month - 3 stars on GitHub - 1 maintainer
@johnhenry/semantic-chunker 0.0.2
A tool for semantic chunking of text3 versions - Latest release: 24 days ago - 40 downloads last month - 3 stars on GitHub - 1 maintainer
rag-core-engine 0.1.3
Framework-agnostic RAG engine: crawl, chunk, embed, store, retrieve, answer — plus general-purpos...4 versions - Latest release: about 2 months ago - 0 stars on GitHub - 1 maintainer
Top 4.2% on npmjs.org
76 versions - Latest release: about 8 hours ago - 5 dependent packages - 12 dependent repositories - 3.78 million downloads last month - 558 stars on GitHub - 1 maintainer
officeparser 8.2.0 💰
A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xls...76 versions - Latest release: about 8 hours ago - 5 dependent packages - 12 dependent repositories - 3.78 million downloads last month - 558 stars on GitHub - 1 maintainer
@dtranllc/kb-genie 1.1.4
Cursor plugin that turns raw technical documents into an agent-optimized knowledge base. This pac...4 versions - Latest release: 2 months ago - 0 downloads last month - 0 stars on GitHub - 1 maintainer
audio-chunkify 1.0.4
Record audio in the browser and automatically split it into chunks — by silence, time, or both. F...4 versions - Latest release: 2 months ago - 34 downloads last month - 1 stars on GitHub - 1 maintainer
@msbayindir/rag-chunker 4.1.0
PDF, Office and Markdown to retrieval-ready chunks — multi-provider (Ollama, Gemini, Claude, Open...5 versions - Latest release: about 14 hours ago - 251 downloads last month - 2 stars on GitHub - 1 maintainer
@badriana/ai-core 1.0.0
AI Engineering Framework — a Prisma-style client for document ingestion, parsing, chunking, embed...9 versions - Latest release: 2 months ago - 87 downloads last month - 1 maintainer
semchunk 1.0.0
A fast and lightweight library for splitting text into semantically meaningful chunks.1 version - Latest release: 7 months ago - 10 downloads last month - 667 stars on GitHub - 1 maintainer
context-doctor 0.35.0
Context and token optimizer for LLM agents: see where Claude Code, Cursor, Codex and Gemini CLI t...52 versions - Latest release: about 19 hours ago - 4.97 thousand downloads last month - 2 stars on GitHub - 1 maintainer
@se-oss/cookies 1.0.1
A lightweight, secure cookie manager for JavaScript and TypeScript with signing, AES-GCM encrypti...2 versions - Latest release: 2 months ago - 585 downloads last month - 3 stars on GitHub - 1 maintainer
js-chunks 0.6.4
Idiomatic TypeScript/JS wrapper around a WASM-backed Rust document chunking engine for RAG — 36 f...5 versions - Latest release: about 1 month ago - 213 downloads last month - 0 stars on GitHub - 1 maintainer
@badriana/rag-core 0.1.0
Lightweight, production-ready RAG Ingestion Engine for document parsing, text normalization, chun...1 version - Latest release: 3 months ago - 1 maintainer
carbites-cli 1.0.0
CLI tool for splitting a single CAR into multiple CARs from the comfort of your terminal.1 version - Latest release: over 5 years ago - 1 dependent package - 1 dependent repositories - 16 downloads last month - 7 stars on GitHub - 1 maintainer
@xberg-io/opencode-tree-sitter-language-pack 1.22.2 💰
Parse and extract code intelligence from 372 programming languages with tree-sitter — structure, ...29 versions - Latest release: 6 days ago - 1.28 thousand downloads last month - 478 stars on GitHub - 1 maintainer
@cogitator-ai/rag 0.7.1
Retrieval Augmented Generation for Cogitator AI agents28 versions - Latest release: 1 day ago - 3.75 thousand downloads last month - 40 stars on GitHub - 1 maintainer
@huggingface/xetchunk-wasm 0.2.0
Content-defined chunking and hashing for Hugging Face Xet storage6 versions - Latest release: about 2 months ago - 643 thousand downloads last month - 2,553 stars on GitHub - 5 maintainers
@mastra/rag 2.6.7
Mastra is the modern TypeScript framework for AI-powered applications and agents.984 versions - Latest release: 9 days ago - 688 thousand downloads last month - 28,846 stars on GitHub - 7 maintainers
excel-reader-mcp 1.0.1
MCP server for reading Excel files with automatic chunking and pagination support2 versions - Latest release: 8 months ago - 34 downloads last month - 0 stars on GitHub - 1 maintainer
chunk-data 0.1.0 💰
Split buffers and streams into smaller chunks1 version - Latest release: about 1 year ago - 3.52 million downloads last month - 75 stars on GitHub - 1 maintainer
Top 0.8% on npmjs.org
84 versions - Latest release: over 8 years ago - 64 dependent packages - 476 dependent repositories - 132 thousand downloads last month - 8,137 stars on GitHub - 1 maintainer
fine-uploader 5.16.2
Multiple file upload plugin with progress-bar, drag-and-drop, direct-to-S3 & Azure uploading, cli...84 versions - Latest release: over 8 years ago - 64 dependent packages - 476 dependent repositories - 132 thousand downloads last month - 8,137 stars on GitHub - 1 maintainer
@pith-hash/pith-cdc 0.1.1 deprecated
FastCDC content-defined chunking SDK: normalized Gear-fingerprint chunk boundaries via the pith-c...5 versions - Latest release: 6 days ago - 0 stars on GitHub - 1 maintainer
@vivantel/virage-strategies 0.2.57
Built-in chunking strategies for @vivantel/rag-core56 versions - Latest release: 4 months ago - 47 downloads last month - 2 stars on GitHub - 1 maintainer
@vivantel/virage-code-chunk-chunker 0.1.76
AST-aware code chunking strategy for @vivantel/virage-core, powered by code-chunk65 versions - Latest release: 2 months ago - 175 downloads last month - 2 stars on GitHub - 1 maintainer
n8n-nodes-document-to-markdown-converter 0.1.0
n8n community node: convert PDF, scanned PDF (OCR), DOCX, PPTX, XLSX, EPUB and HTML to clean Mark...2 versions - Latest release: 2 days ago - 0 stars on GitHub - 1 maintainer
token-chunk 1.2.0
Token-budget-aware semantic chunking for text and Markdown, with heading breadcrumbs and determin...3 versions - Latest release: about 2 months ago - 34 downloads last month - 45 stars on GitHub - 1 maintainer
breadchunks 0.2.3
Heading-aware, token-budgeted semantic chunker for Markdown — for RAG and embedding pipelines.7 versions - Latest release: 4 months ago - 37 downloads last month - 0 stars on GitHub - 1 maintainer
@stackforgeai/copilot-context 1.0.0
Context management, hierarchical chunking, retrieval pipelines, schema-enforced structured output...1 version - Latest release: 5 months ago - 1 maintainer
mdx-corpus 0.1.0
Turn a directory of MDX files into a retrieval-ready JSON corpus. Parse frontmatter, strip JSX, c...1 version - Latest release: 5 months ago - 25 downloads last month - 0 stars on GitHub - 1 maintainer
ingestify 1.0.5
A composable, pipeline-based data ingestion toolkit for Next.js and Node.js projects. Parse, chun...5 versions - Latest release: 6 months ago - 0 stars on GitHub - 1 maintainer
llm-splitter 0.3.0
Efficient, configurable text chunking utility for LLM vectorization. Returns rich chunk metadata.3 versions - Latest release: about 2 months ago - 20.9 thousand downloads last month - 21 stars on GitHub - 7 maintainers
veclite 0.4.3 💰
Client-side vector search. Rust/WASM powered, works where pure JS breaks down.5 versions - Latest release: 5 months ago - 9 stars on GitHub - 1 maintainer
web2md-client 0.1.0
TypeScript client for the Web2MD API: web pages to clean Markdown and heading-aware RAG chunks.2 versions - Latest release: 3 days ago - 0 stars on GitHub - 1 maintainer
web2md-rag-mcp 0.1.0
MCP server for Web2MD: turn any web page into clean Markdown, text or token-bounded RAG chunks vi...2 versions - Latest release: 5 days ago - 0 stars on GitHub - 1 maintainer
@andyed/kinetic-type-engine 0.1.0
Composable physics primitives for kinetic typography. Text segmentation, line breaking, optimal r...1 version - Latest release: 6 months ago - 31 downloads last month - 1 stars on GitHub - 1 maintainer
@pdfluent/extract 0.1.0 💰
PDF to Markdown, JSON and RAG chunks — fast, local, no system dependencies2 versions - Latest release: 3 days ago - 38 stars on GitHub - 1 maintainer
@cjser/chunk-data 0.1.0-cjser.2 💰
Split buffers and streams into smaller chunks1 version - Latest release: 6 months ago - 21 downloads last month - 1 maintainer
@cjser/chunkify 5.0.0-cjser.2 💰
Split an iterable into evenly sized chunks1 version - Latest release: 6 months ago - 1 maintainer
@iflow-mcp/willianpinho-large-file-mcp 1.0.0
Production-ready MCP server for intelligent handling of large files with smart chunking, navigati...1 version - Latest release: 8 months ago - 13 downloads last month - 18 stars on GitHub - 2 maintainers
@willianpinho/large-file-mcp 1.1.1
MCP server for intelligent handling of large files — smart chunking, search, navigation, and stre...3 versions - Latest release: 4 months ago - 1.64 thousand downloads last month - 18 stars on GitHub - 1 maintainer
ragwise 0.1.0
Smart document chunking with embeddings for RAG pipelines1 version - Latest release: 6 months ago - 10 downloads last month - 0 stars on GitHub - 1 maintainer
docparser-core 2.2.1
Enterprise Document Intelligence Engine — Core Package15 versions - Latest release: 5 months ago - 1 maintainer
xlsx-context 1.4.0
Convert .xlsx workbooks into structured context and Markdown for AI applications.4 versions - Latest release: 4 days ago - 0 stars on GitHub - 1 maintainer
@pleias/stratum-client 0.1.1
Official TypeScript / JavaScript client for the Stratum document-chunking API.2 versions - Latest release: 6 months ago - 23 downloads last month - 1 maintainer
@kithjs/voice-router 0.1.0
TTS provider router for Kith — sentence-aware chunking, pronunciation, pacing, fallback.1 version - Latest release: 6 months ago - 0 stars on GitHub - 1 maintainer
@effect-uai/retrieval 0.18.0
Retrieval-pipeline utilities for @effect-uai/core: text chunking, rank fusion, and a Hugging Face...7 versions - Latest release: 15 days ago - 593 downloads last month - 72 stars on GitHub - 1 maintainer
@agentskit/rag 0.7.0 💰
Plug-and-play retrieval-augmented generation for AgentsKit.42 versions - Latest release: 10 days ago - 3.89 thousand downloads last month - 36 stars on GitHub - 1 maintainer
@lyrify/znl-plugin-fs 0.1.3
ZNL file management plugin with chunked transfer, CRUD, and patch support1 version - Latest release: 7 months ago - 0 stars on GitHub - 1 maintainer
mastra-browser-rag 0.0.9
The Retrieval-Augmented Generation (RAG) module contains document processing and embedding utilit...9 versions - Latest release: over 1 year ago - 95 downloads last month - 1 maintainer
@chonkiejs/core 0.0.12 💰
Core chunking library for Chonkie - lightweight and efficient text chunking10 versions - Latest release: 17 days ago - 164 thousand downloads last month - 368 stars on GitHub - 2 maintainers
n8n-nodes-chonkie 0.1.0
n8n community node for chunking text using Chonkie for RAG and NLP pipelines1 version - Latest release: 6 months ago - 81 downloads last month - 2 stars on GitHub - 1 maintainer
rag-skills 1.0.1
Agent skills for RAG: chunking strategies, retrieval methods, vector databases, and performance o...2 versions - Latest release: 6 months ago - 6 stars on GitHub - 1 maintainer
@bunkojp/text-segmentation 0.2.0
Split text into semantic or structural chunks using purely algorithmic strategies. Supports mixed...2 versions - Latest release: 7 months ago - 33 downloads last month - 0 stars on GitHub - 1 maintainer
@winci/bun-chunk 1.3.0
AST-aware code chunking for RAG pipelines — fast, simple, Bun-native14 versions - Latest release: 4 months ago - 1 stars on GitHub - 1 maintainer
message-chunker 0.1.1
Safe preparation module for splitting long rich-text (Markdown) messages for delivery through tra...2 versions - Latest release: 7 months ago - 12 downloads last month - 0 stars on GitHub - 1 maintainer
@intelagent/mcp-file-processor 0.1.1
MCP server for universal text extraction, keyword extraction, language detection, and text chunki...2 versions - Latest release: 7 months ago - 49 downloads last month - 0 stars on GitHub - 1 maintainer
@zetesis/payload-indexer 0.5.0
Generic document indexing library for Payload CMS with support for multiple search backends, embe...13 versions - Latest release: 4 months ago - 396 downloads last month - 0 stars on GitHub - 1 maintainer
eslint-chunker 1.1.0 unpublished
Auto-chunking ESLint runner that updates cache incrementally based on your ESLint config. Perfect...1 version - Latest release: about 1 year ago - 1 stars on GitHub
eslint-plugin-chunkylint 1.8.1
Auto-chunking ESLint runner that updates cache incrementally based on your ESLint config. Perfect...16 versions - Latest release: 2 months ago - 404 downloads last month - 1 stars on GitHub - 1 maintainer
@voltx/rag 0.4.7
VoltX RAG pipeline primitives — document loading, chunking, embedding, retrieval10 versions - Latest release: 7 months ago - 43 downloads last month - 1 stars on GitHub - 1 maintainer
@ruliu/memory-lancedb-pro 1.1.9
OpenClaw enhanced LanceDB memory plugin with hybrid retrieval (Vector + BM25), cross-encoder rera...7 versions - Latest release: 5 months ago - 20 downloads last month - 4,453 stars on GitHub - 1 maintainer
memory-lancedb-pro 1.0.32
OpenClaw enhanced LanceDB memory plugin with hybrid retrieval (Vector + BM25), cross-encoder rera...39 versions - Latest release: 8 months ago - 458 downloads last month - 4,453 stars on GitHub - 1 maintainer
react-native-audio-chunking 1.0.64
React Native module for chunked audio recording65 versions - Latest release: 7 days ago - 186 downloads last month - 1 maintainer
ragkit-ts 0.1.5
Code and document context extraction for AI agents — chunking, symbol extraction, and embedding f...6 versions - Latest release: 8 months ago - 0 stars on GitHub - 1 maintainer
rag-chunk-reorder 0.1.7
RAG chunk reordering, retrieval reranking, and context packing to mitigate lost-in-the-middle in ...8 versions - Latest release: 8 months ago - 217 downloads last month - 1 stars on GitHub - 1 maintainer
@storepress/llm-md-text-splitter 0.0.1
High-performance streaming Markdown text splitter for LLM pipelines and RAG systems. Zero sequenc...1 version - Latest release: 8 months ago - 0 stars on GitHub - 1 maintainer
@fastrag/pageindex 0.3.2
TypeScript SDK for PageIndex hierarchical document indexing and optional vector enhancement.5 versions - Latest release: 4 months ago - 1 maintainer
@divinci-ai/langextract-ts 0.2.0
TypeScript port of Google's LangExtract — structured information extraction from text using LLMs ...2 versions - Latest release: 8 months ago - 1 stars on GitHub - 1 maintainer
@webblackbox/pipeline 0.7.0
Chunking, indexing, blob storage, and archive export pipeline for WebBlackbox recording sessions.13 versions - Latest release: 6 days ago - 20 downloads last month - 15 stars on GitHub - 1 maintainer
@xano-sdk/vector 1.0.1
Plug-and-play vector search & multimodal Gemini embedding pipeline (document/chunk tables, ingest...2 versions - Latest release: 16 days ago - 305 downloads last month - 0 stars on GitHub - 3 maintainers
@ncbijs/jats 0.1.1
Parser for JATS XML full-text articles with RAG chunking2 versions - Latest release: 6 months ago - 38 downloads last month - 1 stars on GitHub - 1 maintainer
@rbalchii/native-atomizer 1.0.1
High-performance C++ text splitter for Node.js - prose and code aware chunking2 versions - Latest release: 8 months ago - 22 downloads last month - 0 stars on GitHub - 1 maintainer
@daviddh/llm-markdown-whatsapp 0.0.6
Transforms Markdown into WhatsApp text format6 versions - Latest release: 8 months ago - 17 stars on GitHub - 1 maintainer
@ayush24k/telezipper 1.5.4 💰
Split folders into multiple 50MB zip files with optional Telegram upload made for personal use.9 versions - Latest release: 8 months ago - 43 downloads last month - 1 stars on GitHub - 1 maintainer
@thebkht/rtc-file-transfer 1.3.0 💰
Peer-to-peer file transfer over WebRTC data channels, with chunking, backpressure, integrity chec...16 versions - Latest release: 21 days ago - 2.44 thousand downloads last month - 3 stars on GitHub - 1 maintainer
nm-mcp-excel-reader 1.0.1
MCP server for reading Excel files with automatic chunking and pagination support2 versions - Latest release: over 1 year ago - 18 downloads last month - 1 maintainer
@liquidau/text-preprocessing 0.1.1
Reproducible document preprocessing; exact UTF-16 source spans, versioned deterministic splitters...3 versions - Latest release: 7 days ago - 0 stars on GitHub - 1 maintainer
@fragments-sdk/context 0.11.3 deprecated
Code intelligence and RAG primitives for design system and codebase indexing37 versions - Latest release: 3 months ago - 1.5 thousand downloads last month - 0 stars on GitHub - 1 maintainer
@serve.zone/containerarchive 0.13.1
content-addressed incremental backup engine with deduplication, compression, and encryption21 versions - Latest release: 8 days ago - 323 downloads last month - 1 maintainer
ep-fine-uploader 5.14.5
Multiple file upload plugin with progress-bar, drag-and-drop, direct-to-S3 & Azure uploading, cli...5 versions - Latest release: over 9 years ago - 1 dependent package - 1 dependent repositories - 108 downloads last month - 8,139 stars on GitHub - 1 maintainer
Top 6.7% on npmjs.org
1 version - Latest release: about 6 years ago - 1 dependent package - 4 dependent repositories - 849 downloads last month - 8,137 stars on GitHub - 1 maintainer
@flowcrypt/fine-uploader 5.16.4
Multiple file upload plugin with progress-bar, drag-and-drop, direct-to-S3 & Azure uploading, cli...1 version - Latest release: about 6 years ago - 1 dependent package - 4 dependent repositories - 849 downloads last month - 8,137 stars on GitHub - 1 maintainer
leoarruda 5.11.11
Multiple file upload plugin with progress-bar, drag-and-drop, direct-to-S3 & Azure uploading, cli...2 versions - Latest release: almost 10 years ago - 1 dependent package - 1 dependent repositories - 13 downloads last month - 8,139 stars on GitHub - 1 maintainer
beta-dev-uploader 5.6.3
[](http://fineuploader.com/)3 versions - Latest release: over 10 years ago - 3 dependent packages - 1 dependent repositories - 31 downloads last month - 8,139 stars on GitHub - 1 maintainer
darmody-fine-uploader 5.12.2
Multiple file upload plugin with progress-bar, drag-and-drop, direct-to-S3 & Azure uploading, cli...3 versions - Latest release: almost 10 years ago - 1 dependent package - 1 dependent repositories - 41 downloads last month - 8,139 stars on GitHub - 1 maintainer
@coderook/cbx 0.3.1
CBX: version control for projects of any size. Snapshots, content-defined chunking, a local histo...4 versions - Latest release: 11 days ago - 484 downloads last month - 0 stars on GitHub - 1 maintainer
chunkr-wasm 1.6.0
Blazingly fast document and text chunking library for LLMs, RAG, and AI agents in WebAssembly (Br...3 versions - Latest release: 10 days ago - 277 downloads last month - 8 stars on GitHub - 1 maintainer
@contextaisdk/rag 1.0.0
ContextAI RAG Engine - Document loading, chunking, and retrieval1 version - Latest release: 9 months ago - 51 downloads last month - 3 stars on GitHub - 1 maintainer
@chonkiejs/chunk 0.10.1 💰
The fastest semantic text chunking library10 versions - Latest release: 7 months ago - 361 stars on GitHub - 2 maintainers
semantic-chunking 3.0.2 💰
Semantically create chunks from large texts. Useful for workflows involving large language models...38 versions - Latest release: 2 months ago - 1.07 thousand downloads last month - 144 stars on GitHub - 1 maintainer
contacted-chunking 2.4.1 💰
Semantically create chunks from large texts. Useful for workflows involving large language models...1 version - Latest release: almost 2 years ago - 9 downloads last month - 144 stars on GitHub - 1 maintainer
ram-chunker 1.0.0
Rapid Asymmetric Maximum (RAM) is a high throughput, hash-less, byte shift-resistant content-defi...1 version - Latest release: over 4 years ago - 2 dependent packages - 2 downloads last month - 0 stars on GitHub - 1 maintainer
n8n-nodes-md2notion 1.6.2
Convert markdown to Notion pages with advanced chunking and error handling - supports large docum...13 versions - Latest release: 8 months ago - 67 downloads last month - 0 stars on GitHub - 1 maintainer
node-fastcdc 1.0.6
NodeJS bindings for fastcdc-rs package with SHA256 hash computation.6 versions - Latest release: 10 months ago - 24 downloads last month - 1 stars on GitHub - 1 maintainer
@lov3kaizen/agentsea-ingest 1.2.1
Comprehensive document processing pipeline for Node.js - PDF, DOCX, HTML, Markdown parsing with i...8 versions - Latest release: 4 months ago - 635 downloads last month - 1 maintainer
Related Keywords
rag
96
llm
69
typescript
56
embeddings
52
ai
49
chunk
47
file
32
vector-search
30
nlp
27
markdown
26
javascript
25
openai
22
retrieval
22
upload
21
nodejs
21
retrieval-augmented-generation
20
mcp
20
text-splitter
18
s3
18
split
18
vector
18
api
17
pdf
16
semantic-search
16
model-context-protocol
15
drag
15
progress
15
browser
15
text-splitting
15
splitting
14
resume
14
text-processing
14
chunker
14
embedding
14
document-processing
14
claude
14
cross-site
13
cross-domain
13
preview
13
jquery-plugin
13
drop
13
jquery
13
multiple
13
widget
13
azure
13
selection
13
file-uploader
13
input
13
streaming
12
aws
12
file-input
12
amazon
12
semantic
12
wasm
12
anthropic
11
vector-database
11
array
11
gemini
11
file-upload
10
cli
10
text
10
n8n-community-node-package
9
tokenizer
9
semantic-chunking
9
text-chunking
9
stream
9
developer-tools
9
webrtc
9
dropzone
9
xlsx
8
deduplication
8
docx
8
cdc
8
similarity
8
chunks
8
parser
8
search
8
splitter
8
pipeline
8
tokenization
8
knowledge-base
8
fineuploader
7
claude-code
7
standalone
7
vanilla-javascript
7
ast
7
ocr
7
esm
7
sentence
7
llms
7
ai-tools
7
generator
7
vanilla-js
7
n8n
7
web-development
7
files
7
ollama
7
pagination
7
tokens
7
javascript-library
7