name: agent-memory-os description: Stop agents from "forgetting, mixing projects, and rotting over time" by giving them a practical memory operating system: global memory, project memory, promotion rules, validation cases, and a maintenance loop.

Agent Memory OS

Build an agent that gets more organized over time instead of more chaotic.

Turn an agent's memory from "a pile of chat history" into a long-term working memory operating system.

What problem this solves

A lot of agents look impressive in short conversations, then collapse under real work:

• they forget what matters
• active projects pollute long-term memory
• useful lessons never become reusable rules
• the system looks good for a week, then decays

This skill exists to fix that.

It helps the agent move from:

• "I remember fragments"

to:

• "I have a stable global brain, project-specific working brains, reusable lessons, validation logic, and a maintenance loop that keeps the whole system healthy."

What makes this different

This is not just:

• note-taking guidance
• a vector-search recipe
• a memory dump strategy

It is a workflow for building an agent memory system with:

• separation of concerns
• promotion paths for reusable knowledge
• validation cases
• operational maintenance rules

Use this skill when

The user says or implies things like:

• "My agent keeps forgetting"
• "Once projects pile up, everything gets messy"
• "I want long-term memory for my AI agent"
• "I need project memory separated from global memory"
• "I want reusable lessons, not just logs"
• "I want to share or standardize an agent memory setup"

Example trigger prompts

This skill should feel natural on prompts like:

• "Help me design long-term memory for my coding agent."
• "My AI assistant keeps mixing projects and forgetting context."
• "I need a reusable memory architecture for multi-project agents."
• "How do I separate durable agent memory from active project memory?"
• "Help me turn chat history into a reusable working-memory system."

What the user gets

By the end of this workflow, the user should have:

1. a memory architecture that separates global and project concerns
2. a minimum project-memory structure
3. routing and promotion rules
4. validation cases to prove the system works
5. a maintenance runbook so it does not decay immediately

Privacy and publishing rule

When using this skill for sharable/public output:

• never expose real user names, private IDs, workspace-specific secrets, session paths, internal message IDs, or private document URLs
• rewrite examples into generalized patterns
• replace personal/project-specific references with neutral placeholders
• do not bundle private memories, raw chat excerpts, or personally identifying workflow traces into the skill

If the user explicitly wants a public/shareable version, treat privacy-preserving abstraction as mandatory, not optional.

Recommended workflow