Search Packages

mnemosyne-engine

LLM Context Compression and Retrieval Engine -- zero dependencies, sub-100ms queries, document + code ingestion

compactbench

Open benchmark for LLM context compaction methods — measures what survives when you replace conversation history with a compacted artifact. Multi-cycle drift, hidden ranked set.

mnemosyne-ollama

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

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

squeez

Squeeze verbose LLM agent tool output down to only the relevant lines

mnemosyne-mcp

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

llama-index-postprocessor-vecr

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