Tamp: Cut LLM context size ~50% without changing your code

Tamp is a token compression proxy that reduces LLM context size by 52.6% for coding agents without requiring any code changes by sitting between agents and APIs to automatically compress tool results like file reads and CLI output. The system uses eight compression stages including JSON minification, deduplication, and neural token pruning to cut costs from $6-15 per coding session to potentially save teams thousands annually while maintaining identical response quality.