shokunin vs AgentRecall-MCP
shokunin: Shokunin provides persistent AI memory for developers with 38 skills, multi-strategy recall (vector + BM25 + temporal), and ChromaDB memory. It is fully offline, zero server costs, and works on Windows and Linux. The system includes MCP servers, declarative self-updates, and a memory test suite.; AgentRecall-MCP: AgentRecall is a learning loop for AI agents that provides persistent, compounding memory. It captures corrections automatically, surfaces past insights across projects, and uses a five-layer memory pyramid with Ebbinghaus decay and Bayesian feedback. Zero cloud, all local markdown files.
TL;DR
Persistent coding context across multiple sessions
Maintain context across AI agent sessions (Claude Code, Cursor, etc.)
Side-by-Side Comparison
Features
Use Cases
FAQ
Deploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.