persistent-memory

Store session history, decisions, and handoffs in portable file-based memory.

Updated Mar 30, 2026

Search Tags:#automation #context #logging #memory #session #ai-agent #memory-protocol

Ready to run

npx skills add https://github.com/radenadri/skills-alena --skill persistent-memory-radenadri

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: persistent-memory
Source: https://github.com/radenadri/skills-alena/tree/main/skills/persistent-memory
Command: npx skills add https://github.com/radenadri/skills-alena --skill persistent-memory-radenadri

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

AI coding sessions often lose context between runs, forcing rework and repeated decisions. This skill provides a portable, file-based memory protocol that captures decisions, context, and learnings so agents can resume work seamlessly.

Core Features & Use Cases

File-based memory store (e.g., .planning/) that records MEMORY.md, sessions/, and handoffs for cross-session continuity.
Cross-session context restoration by reading MEMORY.md and the latest handoff notes to guide planning and execution.
Lightweight compression and archiving to keep MEMORY.md under a reasonable size while preserving history.

Quick Start

Run the /memory init to bootstrap memory, then let the agent read MEMORY.md at the start of each session.

Frequently Asked Questions about persistent-memory

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

FAQPage Schema

How do I keep AI agent context across different coding sessions?▼

To keep AI context across sessions, you use a portable, file-based memory protocol that writes decisions and history to a MEMORY.md file and session logs, allowing any file-reading AI agent to resume work seamlessly without losing prior context.

What is a file-based memory protocol for AI agents?▼

A file-based memory protocol is a standardized structure using a .planning directory to store a MEMORY.md brain, session logs, and handoff notes, enabling cross-session continuity for any AI agent that can read and write files.

How do I initialize cross-session memory for my AI coding project?▼

You initialize cross-session memory by running a memory initialization command to bootstrap a .planning directory, which creates the MEMORY.md file and session log structure for the AI agent to read at the start of each new session.

Can I use this cross-session memory protocol with any AI agent?▼

Yes, you can use this memory protocol with any AI agent that has the ability to read and write files, because it relies on a standardized file-based structure rather than a specific framework or proprietary API integration.

How do I manage file size when logging AI session history and decisions?▼

You manage file size by using the protocol's lightweight compression and archiving features, which keep the MEMORY.md file under a reasonable size while preserving historical session logs and decision records in the .planning directory.

What is the best way to handle AI agent handoffs between sessions?▼

The best way to handle AI agent handoffs is by writing standardized handoff notes within the .planning directory, which the next session reads alongside MEMORY.md to restore context, review past decisions, and guide execution.