x-memory

Manage and retrieve cross-session project memories with Python scripting.

1|Updated Mar 27, 2026
One-click install
npx skills add https://github.com/x-mesh/x-kit --skill x-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: x-memory
Source: https://github.com/x-mesh/x-kit/tree/main/x-memory/skills/memory
Command: npx skills add https://github.com/x-mesh/x-kit --skill x-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of knowledge retention and context re-injection across different project sessions, facilitating better decision-making and learning from past experiences.

Core Features & Use Cases

  • Cross-Session Memory: Persist and recall project decisions, patterns, failures, and learnings.
  • Context Injection: Automatically inject relevant memories into the agent context at session start.
  • Search and Recall: Allow users to search and recall past decisions and patterns when needed.
  • Export and Import: Export memories to files and import them across different projects or machines.

Quick Start

To save a decision, use the command: /xm:memory save "Decision text" --type decision --why "Reason" --tags "Tags".

Frequently Asked Questions about x-memory

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

FAQPage Schema
How do I retain project knowledge and context across different AI agent sessions?

Cross-session memory management allows you to persist and recall project decisions, patterns, and learnings. It automatically injects relevant memories into the agent context at session start to maintain continuity.

How do I save a specific decision and its reasoning for future AI context injection?

To save a decision, use the memory command structure to store the text, specify the type as decision, and include the reason and tags. This records the context for later retrieval and search.

Can I use cross-session memory management to transfer project knowledge to another machine?

Yes, you can export memories to files and import them across different projects or machines. This facilitates knowledge transfer and backup for AI-driven workflows.

Do I need Python to implement context injection and memory storage for my workflows?

Yes, Python is required as a dependency for scripting memory storage and retrieval operations. It executes the underlying logic for managing the cross-session memory database.

What is the best way to search and recall past project failures during an active development session?

You can use the search and recall functionality to query past decisions, patterns, and failures when needed. This allows the AI agent to retrieve specific historical context to inform current tasks.

When should I not rely on automated context injection for AI-driven decision support?

Automated context injection may not suit highly isolated tasks where past project patterns or decisions are irrelevant. Relying on it might introduce unnecessary historical noise into the active agent context.