🦞 LLM Token Compression & Reduction Tool — Cut AI agent token costs by up to 97%. 6-layer deterministic context compression for AI agent workspaces. No LLM required. Prompt compression, context window optimization & cost reduction for any LLM pipeline.

[TMLR 2026] Survey: https://arxiv.org/pdf/2507.20198

📚 Collection of token-level model compression resources.

The official code for the paper: LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs

Token-Oriented Object Notation - A compact data format for reducing token consumption when sending structured data to LLMs (PHP implementation)

Official repository of the paper "A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models"

[CVPR 2026] FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding

[ICLR 2026 Oral] FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging

[ICLR 2026] Official code repository for "⚡️VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration"

😎 Awesome papers on token redundancy reduction

This repo integrates DyCoke's token compression method with VLMs such as Gemma3 and InternVL3

Official implementation of TCSVT 2025 paper: DiViCo: Disentangled Visual Token Compression For Efficient Large Vision-Language Model

[Arxiv 2025 Preprint] HiPrune, a training-free visual token pruning method for VLM acceleration.

[ICLR 2026] Official code of PPE: Positional Preservation Embedding for Token Compression in Multimodal Large Language Models.

🛠️ Implement TOON in PHP for efficient serialization of JSON-like data, optimizing parsing for Large Language Models while maintaining clarity and structure.

Compress React/Next.js files by ~40% for AI assistants. MCP server + encoder.

Maximum meaning, minimum tokens. Rust-based markdown compression for LLM workflows.