chonkiejs
!Chonkie Logo _ðĶ CHONK your texts in TypeScript with Chonkie!âĻ The no-nonsense lightweight and efficient chunking library._ Installation âĒ Usage âĒ Chunkers âĒ Acknowledgements âĒ Citation We built while developing a TypeScript web app that needed fast, on-the-fly text chunking for RAG applications. After trying several existing libraries, we found them either too heavy or not flexible enough for our needs. is a port of the original library, but with some type-safety...
| Entity Passport | |
| Registry ID | gh-model--chonkie-inc--chonkiejs |
| Provider | github |
Cite this model
Academic & Research Attribution
@misc{gh_model__chonkie_inc__chonkiejs,
author = {Chonkie Inc},
title = {chonkiejs Model},
year = {2026},
howpublished = {\url{https://github.com/chonkie-inc/chonkiejs}},
note = {Accessed via Free2AITools Knowledge Fortress}
} ðŽTechnical Deep Dive
Full Specifications [+]âū
Quick Commands
git clone https://github.com/chonkie-inc/chonkiejs âïļ Nexus Index V16.5
ðŽ Index Insight
The Free2AITools Nexus Index for chonkiejs aggregates Popularity (P:0), Freshness (F:0), and Completeness (C:0). The Utility score (U:0) represents deployment readiness and ecosystem adoption.
Verification Authority
ð What's Next?
Technical Deep Dive

ðĶ chonkiejs âĻ
ðĶ CHONK your texts in TypeScript with Chonkie!âĻ The no-nonsense lightweight and efficient chunking library.
Installation âĒ Usage âĒ Chunkers âĒ Acknowledgements âĒ Citation
We built chonkiejs while developing a TypeScript web app that needed fast, on-the-fly text chunking for RAG applications. After trying several existing libraries, we found them either too heavy or not flexible enough for our needs. chonkiejs is a port of the original chonkie library, but with some type-safety and a few extra features to make it more useful for TypeScript developers!
ð Feature-rich: All the CHONKs you'd ever need âĻ Easy to use: Install, Import, CHONK ⥠Fast: CHONK at the max speed of TypeScript! tssssooooooom ðŠķ Light-weight: No bloat, just CHONK ðĶ Cute CHONK mascot: psst it's a pygmy hippo btw âĪïļ Moto Moto's favorite TypeScript library
Chonkie is a chunking library that "just works" âĻ
[!NOTE] This library is not a binding but a port of the original
chonkielibrary written in Python, to TypeScript. This library is still under active development and not at feature parity with the originalchonkielibrary yet. Please bear with us! ðŦ
ðĶ Installation
npm install @chonkiejs/core
ð Usage
import { RecursiveChunker } from '@chonkiejs/core';
// Create a chunker
const chunker = await RecursiveChunker.create({
chunkSize: 512
});
// Chunk your text
const chunks = await chunker.chunk('Your text here...');
// Use the chunks
for (const chunk of chunks) {
console.log(chunk.text);
console.log(`Tokens: ${chunk.tokenCount}`);
}
ðĶ Packages
| Package | Description | Dependencies |
|---|---|---|
| @chonkiejs/core | Local chunking (Recursive, Token) with character-based tokenization | Zero |
| @chonkiejs/cloud | Cloud-based chunkers (Semantic, Neural, Code, etc.) via api.chonkie.ai | @chonkiejs/core |
| @chonkiejs/token | HuggingFace tokenizer support for core chunkers | @huggingface/transformers |
Contributing
Want to help grow Chonkie? Check out CONTRIBUTING.md to get started! Whether you're fixing bugs, adding features, improving docs, or simply leaving a âïļ on the repo, every contribution helps make Chonkie a better CHONK for everyone.
Remember: No contribution is too small for this tiny hippo!
Acknowledgements
Chonkie would like to CHONK its way through a special thanks to all the users and contributors who have helped make this library what it is today! Your feedback, issue reports, and improvements have helped make Chonkie the CHONKIEST it can be.
And of course, special thanks to Moto Moto for endorsing Chonkie with his famous quote:
"I like them big, I like them chonkie in TypeScript" ~ Moto Moto... definitely did not say this
Citation
If you use Chonkie in your research, please cite it as follows:
@software{chonkie2025,
author = {Bhavnick Minhas and Shreyash Nigam},
title = {Chonkie: A no-nonsense fast, lightweight, and efficient text chunking library},
year = {2025},
publisher = {GitHub},
howpublished = {\url{https://github.com/chonkie-inc/chonkie}},
}
ð Quick Start
npm install @chonkiejs/core
ð Limitations & Considerations
- âĒ Benchmark scores may vary based on evaluation methodology and hardware configuration.
- âĒ VRAM requirements are estimates; actual usage depends on quantization and batch size.
- âĒ FNI scores are relative rankings and may change as new models are added.
- âĒ Source: Unknown
AI Summary: Based on GitHub metadata. Not a recommendation.
ðĄïļ Model Transparency Report
Verified data manifest for traceability and transparency.
ð Identity & Source
- id
- gh-model--chonkie-inc--chonkiejs
- source
- github
- author
- Chonkie Inc
- tags
- typescriptaisplitting-algorithmschunkerragretrieval-systemschunking-algorithmtext-splitterllmschonkiesemantic-chunker
âïļ Technical Specs
- architecture
- null
- params billions
- null
- context length
- null
- pipeline tag
- feature-extraction
ð Engagement & Metrics
- likes
- 0
- downloads
- 0
Free2AITools Constitutional Data Pipeline: Curated disclosure mode active. (V15.x Standard)