Semantic Chunking Embedding Tools

Tools for splitting text/code into semantically coherent chunks using embeddings, AST analysis, or similarity metrics for LLM processing. Does NOT include general tokenization, sentence splitting, or document parsing without semantic awareness.

There are 15 semantic chunking tools tracked. 1 score above 50 (established tier). The highest-rated is jparkerweb/semantic-chunking at 61/100 with 134 stars and 5,194 monthly downloads.

Get all 15 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=embeddings&subcategory=semantic-chunking&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	jparkerweb/semantic-chunking 🍱 semantic-chunking ⇢ semantically create chunks from large document for...	61	Established	134	JavaScript
2	drittich/SemanticSlicer 🧠✂️ SemanticSlicer — A smart text chunker for LLM-ready documents.	38	Emerging	36	C#
3	ndgigliotti/afterthoughts Sentence-aware embeddings using late chunking with transformers.	34	Emerging	1	Python
4	smart-models/Normalized-Semantic-Chunker Cutting-edge tool that unlocks the full potential of semantic chunking	32	Emerging	21	Python
5	cspnms/MSchunker Smart text chunker for LLM preprocessing (sections → paragraphs → sentences...	29	Experimental	1	Python
6	ReemHal/Semantic-Text-Segmentation-with-Embeddings Uses GloVe embeddings and greedy sequence segmentation to semantically...	26	Experimental	33	Jupyter Notebook
7	chu2bard/chunkflow Document chunking pipeline for RAG applications	24	Experimental	13	Python
8	zoobz-io/chisel AST-aware code chunking for semantic search and embeddings	24	Experimental	2	Go
9	danielefrisanco/semantic_chunker A lightweight Ruby library for splitting text into topically coherent chunks...	22	Experimental	3	Ruby
10	njyeung/go-semantic-chunking Sementic chunking algorithm in (mostly) Go	21	Experimental	2	Go
11	agamm/semantic-split A Python library to chunk/group your texts based on semantic similarity.	21	Experimental	103	Python
12	IanSousa04/treechunk treechunk é uma biblioteca TypeScript para segmentação semântica de código...	20	Experimental	1	TypeScript
13	SainathPattipati/advanced-chunking-strategies Semantic, agentic, and contextual chunking strategies for RAG with...	19	Experimental	—	Python
14	geleto/semachunk Lightweight Semantic Chunking Library. Plug any embedding provider/API....	15	Experimental	—	JavaScript
15	do-me/js-text-chunker A simple vanilla JS text chunker for hierarchical semantic chunking	10	Experimental	1	HTML

Comparisons in this category

semantic-chunking and Normalized-Semantic-Chunker (61 vs 32) semantic-chunking and go-semantic-chunking (61 vs 21) semantic-chunking and MSchunker (61 vs 29)