Cavemem offers a local-first persistent memory layer for AI coding assistants, compressing session data with a deterministic grammar to reduce token count by 75%. It stores observations in SQLite with hybrid search and runs without a daemon.
vLLM Compressor applies advanced quantization and compression techniques to large language models, enabling optimized inference without requiring full model definitions.
PeaZip is a native, lightweight archive manager supporting 200+ formats across Windows, Linux, macOS, built with Lazarus/FreePascal. It avoids Electron overhead and integrates multiple compression libs.
