tokenslim — High-performance Rust token compression engine for LLM inputs. Plugin-based, 50–95% token savings, AI-export diagnostics

tokenslim is a high-performance Rust engine for LLM token compression. It offers 50-95% token savings via a plugin-based architecture and provides AI-export diagnostics, usable as a CLI, server, IDE plugin, or SDK. This tool significantly reduces input costs and latency for LLM applications by optimizing token usage.

Opening Kapyn…