DNA Memory

What it does

DNA Memory provides a three-layer memory architecture for agents: working memory for current sessions, short-term memory with decay, and long-term memory for consolidated patterns. It adds automated recall, decay, reflection (pattern induction), and linking so agents can remember useful facts, forget noise, and generalise repeated signals into reusable knowledge.

When to use it

Use when an agent must retain user preferences, learn from interactions over days, summarise repeated events into patterns, or automatically surface past decisions during conversations. Triggers include user mentions of "memory", "remember", "reflect", or any request to persist or recall context.

What's included

• Scripts: examples and CLI-style commands in SKILL.md for remember/recall/reflect/decay (no packaged daemon scripts in repo).
• References: conceptual patterns and configuration examples inside the document.
• Instructions: clear operational commands (python scripts examples) describing how to record, recall, reflect, decay, and link memories; configuration parameters and file layout are documented.

Compatible agents

Best used with agents that support persistent local files and scheduled tasks (Python-based agents, Claude/Copilot-style integrations that can call scripts or read workspace files).