Token compression plugin for OpenCode AI — multi-layer filtering, semantic compression, and dynamic context pruning.

Global CLI wrapper for Context-ZIP semantic compression binaries.

Semantic compression for IDE↔LLM communication using radical glyphs — CLI, MCP server, and VS Code extension, with a Context Router, team-shared dictionaries, and compression calibrated against real provider tokenizers.

Lossless semantic compression for LLM contexts — strip grammar, keep facts, save tokens.

Fast math typesetting for the web.

Next-generation AI memory layer with semantic compression and predictive caching

Node.js compression middleware

Official TypeScript SDK for gotcontext.ai — semantic compression REST API (cuts LLM token usage via graph-based PageRank compression).

Semantic compression for Claude and Gemini. O(1) indexed search resolves meaning, depth, and intent in under 5µs. Self-learning, single binary, zero config. 90%+ fewer tokens.

High performance (de)compression in an 8kB package

Client for Contentful's Content Management API

Oxc Minifier Node API

OpenTelemetry semantic conventions

Issues mentioned in `README` should be solved by other approaches: - `.addEventListener()` is blazing fast and is not a real performance issue - to solve issues with ordering in case when regular DOM event propogation is not available consider to use thi

TypeScript definitions for compression

Prepare compressed versions of assets to serve them with Content-Encoding

Middleware and Plugin for request compression.

Ponyfill for smooth scrolling elements into view (if needed!)

Semantic compression for memory files - LLM-readable symbol compression

Compress images in the browser