memory

Manage AI agent long-term memory with OpenMemory for storing and retrieving context.

Updated Aug 23, 2026

Search Tags:#context #ai #memory #persistence #semantic-search #openmemory

Ready to run

npx skills add https://github.com/ksm0709/dotfiles --skill memory-ksm0709

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory
Source: https://github.com/ksm0709/dotfiles/tree/main/opencode/config/skills/memory
Command: npx skills add https://github.com/ksm0709/dotfiles --skill memory-ksm0709

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openmemory-py, python-dotenv, langchain-core, and includes scripts (resource) components.

What problem does it solve?

AI agent long-term memory management to persist and retrieve context, user preferences, and important information via semantic search. Automatic context management is handled by the context-manager plugin. This skill is used when the agent explicitly manipulates memory.

Core Features & Use Cases

Explicit memory operations: /memory add, /memory query, /memory list, /memory delete, /memory status
Semantic search-based retrieval and per-user memory isolation
Context augmentation and learning from user interactions to improve future tasks

Quick Start

Remember this preference: the user likes Python development.

Frequently Asked Questions about memory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I persist AI agent long-term memory with semantic search?▼

You can persist and retrieve AI agent long-term memory by storing conversation context, user preferences, and important information locally under data/memory using OpenMemory with semantic search-based retrieval.

How does semantic search work for retrieving stored AI conversation context?▼

Semantic search for AI conversation context retrieves relevant stored memories by matching meaning rather than exact keywords, enabling accurate recall of user preferences and session information during agent tasks.

Can I isolate memories per user when managing AI agent context?▼

Yes, per-user memory isolation is supported natively. You can store and retrieve individual user preferences and conversation context independently, ensuring agent memory remains scoped to specific users.

What commands are available for explicit memory operations in AI agents?▼

Explicit memory operations include add, query, list, delete, and status commands. These allow direct manipulation of stored memories for saving, retrieving, or removing conversation context and user preferences.

Do I need Python and langchain-core to manage AI agent memory locally?▼

Yes, this relies on openmemory-py, python-dotenv, and langchain-core dependencies to manage AI agent memory. Memories are stored locally under data/memory for local-first access without external services.

When should I use explicit memory operations versus automatic context management for AI agents?▼

Use explicit memory operations when the agent needs to directly save, query, list, or delete specific memories. Automatic context management is handled separately by the context-manager plugin for background augmentation.