Cut LLM context and Claude Code sessions 40–80% without rewriting a byte. Offline, verbatim, with an audit receipt for every block dropped. CLI, MCP server and Claude Code/Open AI Plugin. MIT.
ai token-reduction aiagent prompt-compression aiagents context-compression token-optimizer context-engineering-framework context-engineering-kit jev-model
-
Updated
Oct 12, 2026 - Python