Generate a compact codebase index for AI assistants — saves 50K+ tokens per conversation

docx ↔ LLM translator. Projects .docx office files to Markdown for editing. Projects edits back to OOXML as tracked changes (redlines). Python and Node.js implementations.

Hook-based token compressor for 5 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI). Up to 95% bash compression, signature-mode for code reads, cross-call dedup, MCP server, self-teaching protocol. Zero runtime deps.