SuperCompress - open source LLM prompt compression - is now available on PyPI. 65% fewer tokens, 100% oracle recall.
I just published SuperCompress to PyPI! 🎉
pip install supercompress — that's all it takes.
What is it?
A tiny ~5K parameter CPU policy that scores every line of context for relevance before sending to the LLM. It keeps only what matters for the answer.
The Numbers
A short thread-style post about SuperCompress - open source prompt compression that saves 65% on tokens.
I built an open-source prompt compressor now available on PyPI. Here's the story.
A technical deep-dive into building SuperCompress - a 5K parameter CPU policy that compresses LLM prompts by 65% with 100% oracle…
The AI developer ecosystem is currently obsessed with "lightweight prompt compression." Open-source...
Extractive vs abstractive compression of retrieved chunks. Sentence-level filtering. How to cut tokens without losing the answer.
Context compression is useful, but I stopped trusting the “same answers, fewer tokens” pitch after watching an agent lose one…
