Search Packages

leanctx

Drop-in prompt compression for production LLM applications. Cut Anthropic / OpenAI / Gemini bills by 40-60%.

promptminify

Minify LLM prompts to save tokens — domain-aware, tiktoken-validated, zero regressions

claw-compactor

14-stage Fusion Pipeline for LLM token compression — 15-82% reduction depending on content, zero LLM inference cost, reversible compression, AST-aware code analysis

llama-index-postprocessor-vecr

LlamaIndex postprocessor for vecr-compress: deterministic retention-guaranteed node compression.

context-bench

Benchmark any system that transforms LLM context

contextcrunch

Compress LLM Prompts and save 80%+ on GPT-4 in Python

cutia

Tree-based prompt compression library using cut-then-transform strategy for LLM applications