Token Compression Python Packages

tokenslim

High-performance Rust token compression engine for LLM inputs. Plugin-based, 50–95% token savings, AI-export diagnostics, CLI / Server / IDE / SDK.

claw-compactor

14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.

shadow-web

Local-first Python SDK for AI agents: Shadow DOM flatten, Action Map, SchemaSnap, form fill, security scan, MCP (64–97% token reduction)

tok-protocol

tok is an invisible bridge

twotrim

ultra-lightweight, mathematically robust prompt compression middleware