para-memory-files

Organize persistent agent memory into YAML facts and markdown daily notes.

280|30|Updated Mar 30, 2026

Search Tags:#knowledge management #memory #daily notes #PARA #entity facts #file-based storage #weekly synthesis

Ready to run

npx skills add https://github.com/Undertone0809/rudder --skill para-memory-files-undertone0809

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: para-memory-files
Source: https://github.com/Undertone0809/rudder/tree/main/server/resources/bundled-skills/para-memory-files
Command: npx skills add https://github.com/Undertone0809/rudder --skill para-memory-files-undertone0809

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill solves the problem of losing valuable context between agent sessions by providing a reliable, file-based memory system that preserves facts, timelines, and user operating patterns.

Core Features & Use Cases

PARA knowledge graph: Store durable, entity-scoped facts as atomic YAML in PARA folders and keep summaries refreshed via weekly synthesis.
Daily notes timeline: Record raw “when” information continuously into date-stamped markdown files for traceable recall.
Tacit user knowledge: Maintain instruction-like memory about how the user operates, updated as new patterns are learned.
File-first recall and planning: Retrieve directly from the on-disk sources of truth and manage shared plans in the designated plans directory rather than ad-hoc notes.

Quick Start

Use the para-memory-files skill whenever you need to save or recall durable knowledge across sessions, such as writing an entity’s fact into items.yaml or updating daily notes during a conversation.

Frequently Asked Questions about para-memory-files

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

FAQPage Schema

How do I persist agent memory across sessions using a file-based approach?▼

You can persist agent memory using a file-based three-layer structure under $AGENT_HOME, storing durable context as atomic YAML facts, markdown daily notes, and instruction-style tacit memory to retain knowledge across sessions.

What is the PARA method for organizing persistent agent knowledge?▼

The PARA method organizes persistent agent knowledge into structured folders, storing durable entity-scoped facts as atomic YAML files and keeping summaries refreshed through weekly synthesis for reliable file-based recall.

How do I record daily notes and timelines for agent conversations?▼

Record daily notes by appending raw timeline information into date-stamped markdown files, creating a continuous and traceable log of when events occurred for reliable session recall.

Can I use this memory system to store tacit knowledge about how a user operates?▼

Yes, the system maintains instruction-style tacit memory that captures how the user operates, automatically updating these stored patterns as new behaviors are learned during interactions.

What is the best way to manage shared plans without creating ad-hoc notes?▼

Manage shared plans by storing them in a designated plans directory and retrieving directly from on-disk sources of truth, avoiding scattered ad-hoc notes for better file-first recall.

How does the system handle entity fact updates without losing previous data?▼

Entity fact updates use non-destructive superseding semantics, ensuring that writing new facts into items.yaml preserves the historical context and prevents data loss during knowledge modifications.