SkillAgentSearch skills...

pi-memory

Manage persistent memory across sessions

Install / Use

npx skills add screenfluent/pi --skill pi-memory

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

64/100

Supported Platforms

Universal

Our assessment of pi-memory

pi-memory scores 64/100 on our quality scale, 3937th of 4,613 Development & Engineering skills we index.

Its SKILL.md is 3.8 KB long, well organised into 19 sections with 6 code examples: a solid amount of guidance for an agent.

It has no GitHub stars yet, so there is no community track record; judge it on its content.

Substance
26/30
Structure
20/20
Description
8/15
Adoption
0/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 7 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • Our last check on 2026-10-18 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 74/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

pi-memory compared with similar skills

All 4 of these similar skills score higher than pi-memory; compare them before choosing.

SkillScoreStarsUpdatedFormat
pi-memory (this skill)by screenfluent6407mo agoSKILL.md
taste-skillby Leonxlnx100111.0k1d agoCLAUDE.md
ai-job-searchby ai-job-search-dev10070.0ktodayCLAUDE.md
claude-howtoby luongnv8910046.6k3d agoCLAUDE.md
algorithmic-artby anthropics100177.9k44d agoSKILL.md

Frequently asked questions

How do I install pi-memory?
Run npx skills add screenfluent/pi --skill pi-memory. The install tabs above show the steps for each supported agent.
Which AI agents does pi-memory work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is pi-memory safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 74/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is pi-memory still maintained?
The repository was last updated about 7 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.

name: pi-memory description: Manage persistent memory across sessions. Use when asked to remember, recall, forget, or review what was stored. Covers long-term facts (MEMORY.md), daily session logs, search, and memory housekeeping.

pi-memory — Persistent Memory

A file-based memory system that persists knowledge across sessions using plain Markdown.

Architecture

<base-path>/
├── MEMORY.md              # Long-term curated memory (facts, preferences, decisions)
└── memory/
    ├── 2026-02-11.md      # Daily log — append-only session notes
    ├── 2026-02-10.md
    └── ...
  • MEMORY.md — The "brain". Organized into ## Sections. Survives compaction. Editable in place.
  • memory/YYYY-MM-DD.md — Daily append-only logs. Timestamped entries. One file per day.

The base path defaults to cwd. Override with settings.json:

{ "pi-memory": { "path": "/path/to/memory/dir" } }

Tools

memory_read

Read memory contents.

| target | description | |--------|-------------| | long_term | Read full MEMORY.md | | daily | Read a specific date's log (default: today). Pass date: "YYYY-MM-DD" for other dates. | | list | List all available daily log files |

memory_write

Write to memory.

| target | description | |--------|-------------| | daily | Append a timestamped entry to today's log. Used for session notes, progress, decisions. | | long_term | Update MEMORY.md. Pass section to replace a specific ## Section, or omit to append. |

Long-term memory sections — use section parameter to target:

memory_write target=long_term section="Preferences" content="- Prefers dark theme\n- Terminal-first tools"

This replaces the content under ## Preferences. If the section doesn't exist, it's created.

Daily log entries — auto-timestamped:

memory_write target=daily content="Completed the auth refactor. Using JWT with RS256."

Creates ### HH:MM entry in today's file.

memory_search

Full-text search across MEMORY.md and all daily logs.

memory_search query="JWT" limit=10

Returns matching lines with ±1 line of context, grouped by file.

When to Write Memory

Always write to long-term memory when:

  • User explicitly says "remember this", "save this", "note that..."
  • You learn a new preference, convention, or decision
  • A significant architectural or design choice is made
  • You discover something about the user's workflow or environment

Always write to daily log when:

  • Starting or completing significant work
  • Making key decisions during a task
  • Encountering and resolving blockers
  • At the end of a work session (summarize what was done + next steps)

Section organization for MEMORY.md

Keep MEMORY.md well-organized with clear sections:

# Long-Term Memory

## About [User]
- Key facts, role, location, interests

## Preferences
- Communication style, tool preferences, conventions

## Active Focus
- Current projects and priorities (update as they shift)

## Decisions & Conventions
- Coding conventions, workflow rules, architectural decisions

## People & Relationships
- Key contacts and collaborators

## Recurring Patterns
- Things frequently asked about or worked on

Memory Hygiene

Periodically review and clean up memory:

  1. Deduplicate — Check for repeated sections in MEMORY.md (use memory_read target=long_term)
  2. Archive stale info — Remove outdated decisions or completed project references
  3. Consolidate daily logs — Important patterns from daily logs should be promoted to MEMORY.md
  4. Keep sections focused — Each ## Section should have a clear purpose

System Prompt Injection

At each agent turn, the extension automatically injects into the system prompt:

  • Full MEMORY.md content
  • Yesterday's daily log (if exists)
  • Today's daily log (if exists)

This means the agent always has recent context without needing to call memory_read.

Related Skills

View on GitHub
GitHub Stars0
CategoryDevelopment
Updated7mo ago
Forks0

Trust signals

74/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium2 low