LLMSlim
Semantic prompt compression that never drops instructions.
8 followers
Semantic prompt compression that never drops instructions.
8 followers
Open-source Python package cutting LLM token costs by 40–70% in 1 line of code. Surgically compresses prompts, RAG document contexts, and multi-turn chat logs with guaranteed 100% instruction fidelity.
This is the 2nd launch from LLMSlim. View more
LLMSlim v0.3.0
Launching today
v0.3.0 ships hybrid prompt compression: offline TF-IDF extraction pre-prunes context, then an optional LLM rewrite pass semantically optimizes what remains. Result: 40-70% fewer tokens billed, sub-30ms CPU latency, and 100% retention of system directives, code blocks, and JSON schemas. Works with OpenAI, Anthropic, Gemini, LangChain, LlamaIndex, Ollama and more. Zero dependencies. Pure Python. pip install llmslim
Free
Launch Team
honestly this looks super useful, especially the one line integration. one thing i'd love to see is a built in benchmarking mode that runs the compression against a small eval set you provide and shows you the actual token savings vs quality scores before you ship it to production. would make it way easier to trust the fidelity claim without manually testing every prompt change