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.

AgentRecall-MCP sits in the Memory & Context category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Persistent, compounding memory with 200-line awareness cap. A representative use case is Maintain context across AI agent sessions (Claude Code, Cursor, etc.). The listed license is MIT. GitHub stars are currently 371. Relevant tags include agent-memory, ai-agents.