3 projects
vecr-compress
Auditable, deterministic context compression for LLMs — structured data survives by regex whitelist, every decision logged.
llama-index-postprocessor-vecr
LlamaIndex postprocessor for vecr-compress: deterministic retention-guaranteed node compression.
langchain-vecr-compress
LangChain integration for vecr-compress: deterministic retention-guaranteed LLM context compression.
