Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

para-memory-files — Claude Code skill: PARA memory across sessions

Skill for storing knowledge and facts across IA coder sessions. Organizes memory by the PARA method: projects, areas, resources, and archives in separate files, with vector and keyword search.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add paperclipai/paperclip --skill para-memory-files -a claude-code
Open on GitHub

What para-memory-files does

para-memory-files builds a three-layer memory on files. The first layer is an entity graph in $AGENT_HOME/life/: each entity (project, person, company, topic) stores a quick summary in summary.md and atomic facts in items.yaml. The second layer is daily notes in $AGENT_HOME/memory/YYYY-MM-DD.md, where you write everything that happened. The third is your operating patterns in $AGENT_HOME/MEMORY.md: how you work, what you prefer, which mistakes you repeat.

An entity is created if it is mentioned 3+ times, has a direct relationship to you, or is a significant project. Otherwise, it goes into the daily note. Facts are never deleted, only marked as superseded. Every week, summary.md is rewritten from active facts.

Search through qmd: semantic search with reranking, BM25 keyword search, or pure vector similarity. Plans live in timestamped files so other agents can see them and not confuse old versions with new ones.

What it helps with

  • preserve facts and knowledge so they survive session restarts
  • find information about projects, people and companies even when the wording differs
  • track what happened and when in a single event log
  • learn from mistakes and avoid repeating behavioural patterns

Example prompts for the agent

  • Save this fact to PARA memory: the client asked for a report in PDF by Friday
  • Find all notes about the Acme project, when API issues happened there
  • Remind me how I usually organize files in a new project

How to install para-memory-files

1Skills CLI (Vercel)

npx skills add paperclipai/paperclip --skill para-memory-files -a claude-code

2Manually: put the files in place

~/.claude/skills/para-memory-files/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/para-memory-files/

From the same set2

The whole set →

Similar

course-guide rohitg00 Finds AI Engineering from Scratch lessons for a topic, question, or bug and suggests a next action. Use it when you need a course route for what you are learning. Claude Code CX Codex Cursor +1 4,100installs gcode earthtojake Slices STL, 3MF, and OBJ models into printer-ready G-code through OrcaSlicer. Use it when you need a print file without connecting to the printer. Claude Code CX Codex Cursor +1 9,500installs cli-creator official openai Builds durable command-line tools from API docs, OpenAPI specs, or curl commands. Configures system-wide binaries with JSON output and auth handling. Claude Code CX Codex Cursor +1 3,200installs bambu-labs earthtojake Opens a file in Bambu Connect or Bambu Studio so you pick the printer and hit Print. Handy once a model is already sliced and sitting on disk. Claude Code CX Codex Cursor +1 9,200installs openspec-verify-change openspec Verifies that code implementations match OpenSpec specs, tasks, and design documents before archiving. Useful for validation before finalizing changes. Claude Code CX Codex Cursor +1 3,500installs equity-research official anthropics Builds a stock snapshot from analyst consensus, financials, price history and macro data. Useful when you need to size up a company fast. Claude Code CX Codex Cursor +1 3,200installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs

Questions about para-memory-files

How do I install para-memory-files in Claude Code?

Run npx skills add paperclipai/paperclip --skill para-memory-files -a claude-code, then open ~/.claude/skills/para-memory-files/SKILL.md to verify.

What does para-memory-files do?

It stores durable knowledge, events and personal patterns in files across sessions. Organizes memory by PARA: projects, areas, resources, archives. Lets you search facts through semantic search without losing them on coder reload.

Where are facts stored and how do I search them?

Facts live in $AGENT_HOME/life/ (entities) and $AGENT_HOME/memory/YYYY-MM-DD.md (events). Search via qmd query (semantic), qmd search (keywords), or qmd vsearch (vector similarity). Index the folder first: qmd index $AGENT_HOME.

Source text

SKILL.md · MIT
---
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:

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

```text
$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](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:

```bash
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.

© paperclipai · MIT · paperclipai/paperclip

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor