Agent Memory
Molty-Assistant's memory agent stores, retrieves, and summarizes past conversations for context and improved future interactions.
Install on your platform
We auto-selected Claude Code based on this skillβs supported platforms.
Run in terminal (recommended)
claude mcp add molty-assistant-agent-memory npx -- -y @trustedskills/molty-assistant-agent-memory
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"molty-assistant-agent-memory": {
"command": "npx",
"args": [
"-y",
"@trustedskills/molty-assistant-agent-memory"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The Molty Assistant Agent Memory skill provides agents with the ability to retain and recall information across multiple interactions. It allows agents to remember previous conversations, user preferences, and task details, leading to more personalized and context-aware responses. This memory capability significantly improves agent performance in complex or ongoing tasks.
When to use it
- Long-running projects: When an agent needs to track progress and maintain context over extended periods (e.g., a writing assistant helping draft a novel).
- Personalized experiences: To enable agents to remember user preferences and tailor responses accordingly (e.g., a shopping assistant remembering past purchases).
- Complex workflows: When an agent needs to manage multiple steps or dependencies in a task, ensuring nothing is forgotten (e.g., booking travel arrangements with specific requirements).
- Follow-up conversations: To allow for natural and informed continuation of previous discussions without needing to re-explain context.
Key capabilities
- Persistent memory storage
- Contextual recall across interactions
- User preference retention
- Task detail tracking
Example prompts
- "Remember that I prefer my coffee with oat milk."
- "What was the last thing we discussed about the marketing campaign?"
- "Add 'schedule dentist appointment' to my task list, and remember itβs for next Tuesday at 2pm."
Tips & gotchas
The agent memory skill requires careful prompt engineering to ensure information is stored and retrieved correctly. Be explicit in your instructions when adding or referencing items within the agent's memory.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates β what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
π Community
Passed automated security scans.