Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Self-improving learning engine for Claude Code. Extracts signals from every session (corrections, successes, confusion), runs periodic reflections, and evolves behavioral frameworks through evidence tiers (hypothesis → observed → validated). Frameworks that keep working get promoted, bad ones get retired. 9 MCP tools, automatic hooks, phase-adaptive learning. Single dependency, local-only. npx claude-soul init --starter
Graph-structured session memory for LLMs. Local OpenAI-compatible proxy that extracts tasks, decisions, and files into a typed knowledge graph, auto-checkpoints before context overflow, and resumes any session in 250 tokens. 6 MCP tools including whydecision (traces why a decision changed, with reasons and evidence). pip install tokenmizer