sqz-mcp vs lean-ctx vs sqz-engine

MCP server for sqz — expose LLM context compression over Model Context Protocol (stdio/SSE)

Context Runtime for AI Agents with CCP. 71 MCP tools, 10 read modes, 95+ compression patterns, cross-session memory (CCP), persistent AI knowledge with temporal facts + contradiction detection, multi-agent context sharing, LITM-aware positioning, AAAK compact format, adaptive compression with Thompson Sampling bandits. Supports 24+ AI tools. Reduces LLM token consumption by up to 99%.

Adaptive multi-pass LLM context compression engine — content-aware pipeline with AST parsing, token counting, session persistence, and budget tracking