🦞 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.

JavaScript/TypeScript implementation of LLMLingua-2 (Experimental)

Python command-line tool for interacting with AI models through the OpenRouter API/Cloudflare AI Gateway, or local self-hosted Ollama. Optionally support Microsoft LLMLingua prompt token compression

Rolling context compression for Claude Code — never hit the context wall. Auto-compresses old messages while keeping recent context verbatim. Zero config, zero latency. Works as a Claude Code plugin.

CUTIA: compress prompts while preserving quality

This repository is the official implementation of Generative Context Distillation.

TOON for TYPO3 — a compact, human-readable, and token-efficient data format for AI prompts & LLM contexts. Perfect for ChatGPT, Gemini, Claude, Mistral, and OpenAI integrations (JSON ⇄ TOON).

API gateway for LLM prompt compression with policy enforcement built on LLMLingua. Demonstrates cost control, prompt safety, and LLM execution boundaries.

Compress LLM Prompts and save 80%+ on GPT-4 in Python

End-to-End Python implementation of CompactPrompt (Choi et al., 2025): a unified pipeline for LLM prompt and data compression. Features modular compression pipeline with dependency-driven phrase pruning, reversible n-gram encoding, K-means quantization, and embedding-based exemplar selection. Achieves 2-4x token reduction while preserving accuracy.

Enhance the performance and cost-efficiency of large-scale Retrieval Augmented Generation (RAG) applications. Learn to integrate vector search with traditional database operations and apply techniques like prefiltering, postfiltering, projection, and prompt compression.

This repository contains the code and data of the paper titled "FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution."

A fast, Unix-style CLI tool for semantic prompt compression. Cuts LLM prompt tokens by 10-20x with >90% fidelity, saving costs and latency.

Prompt compaction and shorthand codec for LLM workflows

CATALYST - Lightning-fast optimization plugin for Claude Code + Ollama. Achieves 3-4x speedup through intelligent prompt compression, smart caching, and task-aware planning. Zero dependencies, MIT licensed, production-ready.

RL-Prompt-Compression employs graph-enhanced reinforcement learning with a Phi-3 compressor trained via GRPO using a TinyLlama evaluator and a MiniLM cross-encoder feedback model, to optimize prompt compression and improve model efficiency.

LLM context compression proxy — 40-70% token savings, zero code changes

PAKT: Lossless prompt compression for LLMs. 30-50% fewer tokens on JSON/YAML/CSV/Markdown. Perfect round-trip fidelity. TypeScript library + CLI + Chrome extension + Tauri desktop app.

Benchmark any system that transforms LLM context: compressors, RAG rerankers, memory managers, and more.