Fast local token shrinking for LLM context: prose compression + fence-aware code safety
In the Coding AI & assistants space, TokenShrinkWrapper takes a focused approach. It focuses on reducing token usage in LLM prompts while preserving code and prose integrity. TokenShrinkWrapper is an open-source project aimed at LLM developers and prompt engineers. The project is open source (MIT). The product ships for the web and the command line, and it can be self-hosted.
It is developed by dferlemann, and the product first shipped in 2026. Across PulseGate's embedding index, TokenShrinkWrapper has few near neighbours, marking it as relatively distinct. Among its 4 catalogued features are token compression, prose shrinking, and code safety.
Latest indexed changes and source events
Other apps tracked under the same category.
