llmlingua

Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code. Python SDK, LLMLingua-2, MIT.

JavaScript/TypeScript implementation of LLMLingua-2 (Experimental)

Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.

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

TokenPack packs long documents, codebases, PDFs, and folders into compact, evidence-dense LLM context using local embeddings, evidence scoring, and budget-aware selection.

LLMLingua-2 prompt compression hook for Claude Code — cut token usage by ~55%

A Claude Code skill that shrinks massive prompts and files using LLMLingua to save tokens.

Multi-layer token optimization for LLM applications — compress prompts, map codebases, reduce output. Zero required dependencies.

Instant text, video & audio summaries on iOS Flutter client · Python (llmlingua) & Node.js (Whisper) services · MongoDB · RevenueCat IAP

A .NET 10 CLI utility for LLM prompt compression using Microsoft's LLMLingua-2 to hit target token budgets.

Self-hosted HTTP sidecar for LLM context compression. Reduce token costs 3–5× before calling any AI API — powered by LLMLingua-2 and MarkItDown. No proxy, no API keys, no GPU required.

Benchmarking GenAI compute efficiency through context compression and model selection.

Lindsay Clancy trial transcript: all 22 days of Commonwealth v. Lindsay Clancy (Plymouth County, MA, 2026), plus compressed single-file versions that fit an LLM context window. Source: lindsayclancytrial.com (Rev).

Small Lab — AI Research Workbench: human-readable agent workflows, reproducible LLMLingua-2 experiments, and DeepSeek serverless inference on DigitalOcean.

Context compression for AI agents: LLMLingua-2 successor that keeps IDs, paths and numbers intact. 68.8% vs 53.4% QA at 50% kept.

Hybrid prompt compression toolkit for LLM workflows

Experimental capacity-aware cognitive compression for AI agents — compile large context, evidence, constraints, and procedures into small-model-ready packages with provenance and fidelity checks.