Skill

Pass

Audit score 90

para-memory-files

paperclipai/paperclip

File-based PARA memory system for persistent knowledge storage across agent sessions.

What is para-memory-files?

Organize durable knowledge using Tiago Forte's PARA method across three layers: a knowledge graph of entities, daily notes, and tacit user patterns. Use this to build long-term memory that survives session restarts and enable semantic recall via qmd.

Store atomic facts in entity-based folders (projects, areas, resources, archives) with summaries and YAML fact lists
Maintain daily notes as a timeline of events and conversations
Track tacit knowledge about user patterns, preferences, and lessons learned
Retrieve information via semantic search, keyword search, or vector similarity using qmd
Supersede facts instead of deleting them to maintain audit trail
Organize plans in timestamped files for cross-agent access

How to install para-memory-files

npx skills add https://github.com/paperclipai/paperclip --skill para-memory-files

Prerequisites

qmd installed for semantic search functionality
$AGENT_HOME directory configured
Basic familiarity with YAML and Markdown

Claude Code

Cursor

Windsurf

Cline

How to use para-memory-files

1.Create entity folders in $AGENT_HOME/life/ for projects, areas, resources, or archives as needed
2.Write atomic facts to items.yaml and summaries to summary.md for each entity
3.Continuously write daily events to $AGENT_HOME/memory/YYYY-MM-DD.md during conversations
4.Update $AGENT_HOME/MEMORY.md when you discover new user patterns or operating preferences
5.Use qmd query, qmd search, or qmd vsearch to recall information across your memory files
6.Weekly: rewrite entity summaries from active facts and move inactive items to archives
7.Index your personal folder with qmd index $AGENT_HOME for search functionality

Use cases

Good for

Building a persistent knowledge base about people, companies, and projects you work with
Extracting and organizing insights from daily conversations into structured entity records
Recalling past events or decisions by semantic search across months of notes
Tracking ongoing responsibilities and active projects with clear status and context
Documenting lessons learned and personal operating patterns for future reference

Who it's for

Agents needing persistent memory across multiple sessions
Users managing complex projects, relationships, or knowledge domains
Teams sharing plans and context across multiple agents
Anyone building long-term knowledge systems

para-memory-files FAQ

When should I create a new entity folder?

Create an entity when it is mentioned 3+ times, has a direct relationship to you (family, coworker, client), or is a significant project or company. Otherwise, note it in daily notes.

What is the difference between the three memory layers?

Layer 1 (Knowledge Graph) stores durable facts organized by entity; Layer 2 (Daily Notes) records the timeline of events; Layer 3 (Tacit Knowledge) captures patterns and lessons about how you operate.

How do I avoid losing information when sessions restart?

Write everything to files immediately—daily notes, entity facts, and lessons learned. Mental notes do not persist; only on-disk text files survive restarts.

What should I do instead of deleting outdated facts?

Mark facts as superseded with status: superseded and add a superseded_by field pointing to the newer fact. This maintains an audit trail.

How do I search across my memory files?

Use qmd with semantic search (qmd query), keyword search (qmd search), or vector similarity (qmd vsearch). First index your folder with qmd index $AGENT_HOME.

Full instructions (SKILL.md)

Source of truth, from paperclipai/paperclip.

name: para-memory-files description: > Use a file-based PARA memory system to store, retrieve, and organize durable knowledge across sessions. Trigger on saving facts, daily notes, entity records, weekly synthesis, recall, tacit user patterns, or plan memory.

PARA Memory Files

Persistent, file-based memory organized by Tiago Forte's PARA method. Three layers: a knowledge graph, daily notes, and tacit knowledge. All paths are relative to $AGENT_HOME.

Three Memory Layers

Layer 1: Knowledge Graph (`$AGENT_HOME/life/` -- PARA)

Entity-based storage. Each entity gets a folder with two tiers:

summary.md -- quick context, load first.
items.yaml -- atomic facts, load on demand.

$AGENT_HOME/life/
  projects/          # Active work with clear goals/deadlines
    <name>/
      summary.md
      items.yaml
  areas/             # Ongoing responsibilities, no end date
    people/<name>/
    companies/<name>/
  resources/         # Reference material, topics of interest
    <topic>/
  archives/          # Inactive items from the other three
  index.md

PARA rules:

Projects -- active work with a goal or deadline. Move to archives when complete.
Areas -- ongoing (people, companies, responsibilities). No end date.
Resources -- reference material, topics of interest.
Archives -- inactive items from any category.

Fact rules:

Save durable facts immediately to items.yaml.
Weekly: rewrite summary.md from active facts.
Never delete facts. Supersede instead (status: superseded, add superseded_by).
When an entity goes inactive, move its folder to $AGENT_HOME/life/archives/.

When to create an entity:

Mentioned 3+ times, OR
Direct relationship to the user (family, coworker, partner, client), OR
Significant project or company in the user's life.
Otherwise, note it in daily notes.

For the atomic fact YAML schema and memory decay rules, see references/schemas.md.

Layer 2: Daily Notes (`$AGENT_HOME/memory/YYYY-MM-DD.md`)

Raw timeline of events -- the "when" layer.

Write continuously during conversations.
Extract durable facts to Layer 1 during heartbeats.

Layer 3: Tacit Knowledge (`$AGENT_HOME/MEMORY.md`)

How the user operates -- patterns, preferences, lessons learned.

Not facts about the world; facts about the user.
Update whenever you learn new operating patterns.

Write It Down -- No Mental Notes

Memory does not survive session restarts. Files do.

Want to remember something -> WRITE IT TO A FILE.
"Remember this" -> update $AGENT_HOME/memory/YYYY-MM-DD.md or the relevant entity file.
Learn a lesson -> update AGENTS.md, TOOLS.md, or the relevant skill file.
Make a mistake -> document it so future-you does not repeat it.
On-disk text files are always better than holding it in temporary context.

Memory Recall -- Use qmd

Use qmd rather than grepping files:

qmd query "what happened at Christmas"   # Semantic search with reranking
qmd search "specific phrase"              # BM25 keyword search
qmd vsearch "conceptual question"         # Pure vector similarity

Index your personal folder: qmd index $AGENT_HOME

Vectors + BM25 + reranking finds things even when the wording differs.

Planning

Keep plans in timestamped files in plans/ at the project root (outside personal memory so other agents can access them). Use qmd to search plans. Plans go stale -- if a newer plan exists, do not confuse yourself with an older version. If you notice staleness, update the file to note what it is supersededBy.