93 skills found · Page 1 of 4
open-compress / Claw Compactor14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
cokeshao / Awesome Multimodal Token Compression[TMLR 2026] Survey: https://arxiv.org/pdf/2507.20198
xuyang-liu16 / Awesome Token Level Model Compression📚 Collection of token-level model compression resources.
Hannibal046 / XRAG[Neurips2024] Source code for xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
yaolinli / MLLM Token CompressionTowards Efficient Multimodal Large Language Models: A Survey on Token Compression
S1LV4 / Th0th🏛️ Ancient knowledge keeper for modern code. Semantic search with 98% token reduction for AI assistants. Features: hybrid search, context compression, persistent memory.
HelgeSverre / Toon PhpToken-Oriented Object Notation - A compact data format for reducing token consumption when sending structured data to LLMs (PHP implementation)
HumanMLLM / LLaVA ScissorThe official code for the paper: LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs
KD-TAO / DyCoke[CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
OpenGVLab / DiffRate[ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging techniques, while incorporating a differentiable compression rate.
ppgranger / Token SaverContent-aware output compression for AI coding assistants. Replaces blind truncation with intelligent strategies per file type: structural summaries for code, schema extraction for configs, error-focused filtering for logs, and smart sampling for CSVs. Saves tokens while preserving what the model actually needs.
HVision-NKU / GlimpsePruneOfficial repository of the paper "A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models"
opendilab / HH Codec[ICML 2025 Tokenization Workshop] HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling
Huzaifa785 / Context CompressorAI-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.
yaolinli / DeCoCode for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models
turingmotors / One D Piece[ICML 2025 Tokshop] One-D-Piece: Image Tokenizer Meets Quality-Controllable Compression
MaxDevv / Un LOCCUn-LOCC: Universal Lossy Optical Context Compression for Vision-Based Language Models Achieve nearly 3x token compression at over 93% retrieval accuracy using existing Vision-Language Models.
KD-TAO / OmniZipOmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
asahi417 / Lm Vocab TrimmerVocabulary Trimming (VT) is a model compression technique, which reduces a multilingual LM vocabulary to a target language by deleting irrelevant tokens from its vocabulary. This repository contains a python-library vocabtrimmer, that remove irrelevant tokens from a multilingual LM vocabulary for the target language.
ilang-ai / AutocodeYou say it. AutoCode builds it. 38 professional skills, persistent memory, 60%+ dev cost savings. Zero dependencies. Free forever.
