Tag: agentic-memory
ThumbGate Feedback Capture Skill
Captures explicit user feedback into structured memories and prevention rules to facilitate agentic learning. It logs context, failures, and corrective actions to refine future agent performance.
NEXO Brain Cognitive Memory System
A local-first cognitive memory system for AI agents implementing the Atkinson-Shiffrin model with semantic RAG and error prevention. It provides episodic memory, trust scoring, and automated memory decay for persistent agent intelligence.
Persistent Agent Memory via MCP
Provides agents with persistent memory across sessions by allowing them to recall past feedback and follow auto-generated prevention rules. The system uses an MCP server to capture task outcomes and track performance trends locally.
Pattern-based memory synthesis skill
Synthesises recurring patterns, user preferences, and decision histories from stored memories into a structured digest. It avoids raw memory dumps by providing insights into identity, open threads, and current emotional states.
Codifying Habits into Cognitive Reflexes
This skill observes recurring user patterns and procedural knowledge, codifying them into a permanent, auto-firing skill file. It functions as a meta-instinct, allowing the system to autonomously generate and install customized capabilities…
Persistent Long-Term Memory Triage Protocol
Evaluates conversational turns to extract, organise, and persist durable, actionable facts into long-term memory using the mem0 framework. It employs a multi-gate decision process to ensure stored information is novel, factual, and secure.
Mem0 MCP Memory Management Protocol
A protocol for agents to maintain persistent context across sessions using Mem0 MCP tools, featuring strategic memory retrieval and structured storage with metadata filtering.