14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
-
Updated
Apr 1, 2026 - Python
14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
Help AI agents use fewer tokens and keep more useful context. Reversible code, JSON and text compression, persistent memory, focused reads and version-aware edits.
Windowed, reversible context management for DeepSeek Harness (DSH): compression, historical retrieval, and native compaction integration.
Automate content research, card news, images, voice, and video from one prompt with an end-to-end Claude Code content pipeline
To associate your repository with the reversible-compression topic, visit your repo's landing page and select "manage topics."