AgentRecall-X

AgentRecall is a unique agent memory system that not only stores human corrections but also measures whether these corrections lead to actual behavioral changes in the agent across sessions. It provides a governed corrections ledger and a measurement harness to track and verify if an agent stops repeating past mistakes.

AgentRecall-X 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 Governed corrections ledger with severity, evidence, and outcome tracking.. A representative use case is Ensuring AI agents learn from past mistakes and avoid repeating errors across sessions.. The listed license is MIT. GitHub stars are currently 371. Relevant tags include Agent Memory, LLM Learning Loop.