persistent-memory

Name: persistent-memory
Availability: InStock
Author: Aayushsoam

Preserve and retrieve task context and decision history across sessions.

1|Updated Mar 31, 2026

Search Tags:#workflow #planning #context #logging #memory #session #observation

Ready to run

npx skills add https://github.com/aayushsoam/clawbot-plus --skill persistent-memory-aayushsoam

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Keeps a persistent record of decisions and task context across interactions to support continuous, coherent workflows.

Core Features & Use Cases

Context injection: Maintain an ongoing memory log per task, enabling traceability of actions and decisions across steps.
Observation logging: Automatically record every tool usage as an Observation to build a verifiable timeline.
Session lifecycle: Provide pre-session review, in-turn consistency checks, and post-session summaries to reduce rework.
Knowledge retrieval: Read artifacts from prior sessions to inform current decisions without guessing history.

Quick Start

Enable persistent memory mode to start saving your task context across turns.

Frequently Asked Questions about persistent-memory

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

FAQPage Schema

How do I preserve task context and decision history across multiple sessions?▼

To preserve task context across sessions, maintain a memory log using a task.md file or .memory/ directory to record decisions, observations, and summaries. This ensures traceability and coherent continuous workflows without guessing prior history.

How does observation logging work for multi-step planning tasks?▼

Observation logging for multi-step planning works by automatically recording every tool usage as a standardized Observation. This builds a verifiable timeline of actions and decisions, ensuring full traceability of context injection throughout the task lifecycle.

What is the best way to retrieve knowledge artifacts from prior sessions?▼

The best way to retrieve knowledge artifacts from prior sessions is to read the saved memory logs directly. Injecting this historical context into your current decisions prevents rework and eliminates the need to guess previous task history.

Do I need a specific directory structure to enable persistent memory?▼

Yes, enabling persistent memory imposes requirements for standardized memory logs, typically utilizing a task.md file or a .memory/ directory. You must also provide a clear end-of-session summary to ensure traceability within your workflow.

When do I need context injection for long-running tasks?▼

You need context injection for long-running tasks when working through multi-step planning scenarios that span multiple sessions. It maintains an ongoing memory log per task, enabling pre-session review and in-turn consistency checks to reduce rework.