What does provenance-aware priority handling do?

It prevents untrusted RAG, tool, and assistant content from gaining protected priority solely through imperative or safety-critical wording.

Does LLMSlim prevent prompt injection?

No. It mitigates compression-induced instruction elevation and applications still need defense in depth.

The default extractive strategy runs locally. Rewrite and hybrid strategies use a caller-supplied provider.

Getting Started 3 min readUpdated August 2026

Python context compression with measured, documented behavior.

Install the Python package with pip. Optional extras enable exact token counts.

terminal

pip install llmslim
# Optional exact token counter
pip install 'llmslim[fast-tokens]'

The GENERAL role preserves the legacy compress(text) behavior.

example.py

from llmslim import compress

result = compress(long_context, target_ratio=0.5)
print(result.compressed_text)
print(result.token_counter_used)

Frequently asked questions

Does LLMSlim require an LLM provider?

No. Extractive compression runs locally. Rewrite and hybrid strategies require a caller-supplied provider.