text-compression

Star

Here are 82 public repositories matching this topic...

Language:All

Filter by language

All82 Python19 C++15 C10 Java7 HTML6 JavaScript6 TypeScript4 C#3 Jupyter Notebook3 Haskell2

Sort:Most stars

Sort options

Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated

Huzaifa785 /context-compressor

Star64

AI-powered text compression library for RAG systems and API calls. Reduce token usage by up to 50-60% while preserving semantic meaning with advanced compression strategies.

python nlp machine-learning ai transformers openai neural-networks summarization text-processing text-compression cost-optimization extractive rag fastapi llm langchain anthropic token-reduction semantic-compression api-optimization

UpdatedAug 16, 2025
Python

rwanwork /Re-Pair

Star25

Offline Dictionary-based Compression (Re-Pair, Recursive Pairing)

c compression offline compression-algorithm text-compression

UpdatedMay 29, 2023
C

WangXuan95 /LLMA

Star21

LLMA = LLM + Arithmetic coder, which use LLM to do insane text data compression. LLMA=大模型+算术编码，它能使用LLM对文本数据进行暴力的压缩，达到极高的压缩率。

gzip data-compression lzma xz arithmetic-coding text-compression cmix paq llm

UpdatedNov 24, 2024
Python

Extreme inline text compression for HTML / JS. A custom pipeline that generates stand-alone HTML or JS files which embed competitively compressed self-extracting text, with file sizes of 25% - 40% the original.

base64 compression yenc binary-to-text text-compression burrows-wheeler-transform huffman-decoder base122 move-to-front png-bootstrap base125 crenc

UpdatedJan 12, 2025
Python

jparkerweb /llm-distillery

Star11

🍶 llm-distillery ⇢ use LLMs to run map-reduce summarization tasks on large documents until a target token size is met.

text-summarization text-processing tokenization text-compression token-management openai-api llm large-language-model semantic-chunking text-distillation ai-text-reduction

UpdatedFeb 28, 2025
JavaScript

fehmisener /LZ77-and-Deflate-Compressor

Star11

This project is about the implementation of the LZ77 and Deflate COMPRESSION algorithm.

c data lz77 data-compression compression-algorithm deflate text-compression deflate-algorithm lz77-compression-algorithm data-compressor lzz deflate-compare-lz77

UpdatedAug 27, 2020
C

tarek99samy /Huffman-Code-Visulizer

Star10

A simple visualization for huffman tree, which is used in encoding text.

javascript css html5 huffman-coding huffman-compression-algorithm text-compression

UpdatedOct 1, 2022
JavaScript

typio /entreepy

Star9

Text compression tool ⚡

compression zig huffman text-compression entropy-coding

UpdatedMar 14, 2024
Zig

thezaza101 /textdiffcore

Star8

Cross platform diff engine for .net core used to compare string values and generate a comparison output

html markdown diff dotnet dotnetcore dotnet-core text-compression myers-algorithm compare-strings

UpdatedFeb 27, 2024
C#

TejveerSingh13 /Image-Steganography

Star6

Using Huffman code to encode and compress the secret text data along with using histogram shifting to encode the data into the image.

steganography image-encryption image-steganography text-compression text-encoding steganography-algorithms image-encoding python-steganography

UpdatedMay 1, 2023
Python

Ferki-git-creator /fsp

Star6

Easy data compression algorithm.

open-source binary-data pattern-matching innovation data-compression data-processing compression-algorithm text-compression fsp algorithm-design file-compression delta-encoding computer-science-project similarity-detection lossless-compression efficient-storage lgpl-3-0 compression-technique

UpdatedSep 11, 2025
HTML

Sahil-4555 /lZ77_Compression_Decompression

Star5

LZ77 algorithm, providing efficient lossless data compression and decompression capabilities. It offers a reliable and flexible solution for reducing file sizes in various programming languages.

c data algorithms cpp data-compression compression-algorithm deflate text-compression lz77-compression-algorithm data-compressor lzz deflate-compare-lz77 deflate-compression