Open source guide
Open-source token compression
SuperCompress is an open-source (MIT) token compression engine for teams that want transparent preprocessing.
Why open source matters
- Transparency - Inspect exactly how compression works
- Control - Run locally, no external API dependencies
- No vendor lock-in - MIT license
Installation and quick start
pip install supercompress
from supercompress import Compressor
comp = Compressor()
result = comp.compress(context, query)Frequently asked questions
Can I run SuperCompress locally?
Yes. Install the Python package. No GPU needed.
What license is it under?
MIT - free to use, modify, and distribute.
Build with less context
Put compression in front of your next LLM call.
Use the hosted API or run SuperCompress locally. Keep the evidence, drop the token waste, and measure the savings before it reaches your model.