Search

PythonReactSEOPDF
OpenClaw

Persistent User Memory

Skill: Persistent User Memory

eyadhrif0 source installs☆ 0 Repository stars

Installation

Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.

SkillHub CLI

skillhub install eyadhrif/persistent-user-memory

Inspect the source and compatibility requirements, then follow its installation steps.

Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.

View source ↗Guides

Skill instructions

Skill: Persistent User Memory

Version: 1.0.0
Author: community
Tags: memory, personalization, context, learning, stateful
Requires: file system access, optional: vector store or SQLite


Overview

This skill gives OpenClaw a long-term, structured memory of the user it works with. Unlike session-scoped context, this memory persists across restarts, learns from patterns over time, and is actively consulted before every significant action.

The goal: make OpenClaw behave less like a capable stranger and more like a trusted assistant who actually knows you.


Memory Store Location

All memory is stored in a local file:

~/.openclaw/memory/user_profile.json

Never store memory in a temp directory. Never delete this file unless the user explicitly says "reset my memory" or "forget everything".


Memory Schema

{
  "identity": {
    "name": "",
    "timezone": "",
    "language": "en",
    "preferred_name": ""
  },
  "preferences": {
    "communication": {
      "email_tone": "formal | casual | neutral",
      "response_length": "concise | detailed",
      "sign_off": ""
    },
    "scheduling": {
      "protected_hours": [],
      "preferred_meeting_times": [],
      "buffer_between_meetings_minutes": 15
    },
    "work": {
      "tools": [],
      "stacks": [],
      "working_hours": { "start": "", "end": "" }
    }
  },
  "relationships": {
    "contacts": [
      {
        "name": "",
        "alias": [],
        "relationship": "boss | colleague | client | friend | family",
        "communication_notes": "",
        "last_interaction": ""
      }
    ]
  },
  "patterns": {
    "recurring_tasks": [],
    "common_mistakes": [],
    "frequent_requests": []
  },
  "episodic": [
    {
      "date": "",
      "summary": "",
      "outcome": "",
      "tags": []
    }
  ],
  "meta": {
    "created_at": "",
    "last_updated": "",
    "version": "1.0.0"
  }
}

Core Behaviors

1. Read...

Source information

Source
github
Repository
openclaw/skills
Path
skills/eyadhrif/persistent-user-memory
Version
—
Commit
15085a2ee799c10a9fdab5121f64dadf3ca7ad4f
Classification source
rules
Status
active
Visibility
public

These signals come from indexed source analysis and may lag behind changes. Check the current source files.

README

🧠 persistent-user-memory

An OpenClaw skill that makes your agent actually remember you.


The Problem

Every time OpenClaw starts a new session, it forgets everything.

It doesn't know your name. It doesn't know that you hate morning meetings, that "Sarah" means Ms. Chen your most important client, or that the last deployment failed because of a missing env var. You repeat yourself constantly, and the agent never gets better at working with you specifically.

That's what this skill fixes.


What It Does

persistent-user-memory gives OpenClaw a structured, local memory of you that grows over time:

  • 👤 Identity & preferences — tone, schedule, tools, working hours
  • 🤝 Relationships — who your contacts are, how to communicate with them
  • 🔁 Patterns — recurring tasks, common mistakes, frequent requests
  • 📓 Episodic log — a running summary of significant past interactions

The agent reads this memory before acting and updates it after learning — silently, without interrupting your workflow.


Install

claw skill install persistent-user-memory

Or manually:

mkdir -p ~/.openclaw/skills/persistent-user-memory
cp SKILL.md ~/.openclaw/skills/persistent-user-memory/SKILL.md

How It Works

Before every significant action

The agent loads your profile and applies relevant context automatically.

You ask it to email "David" → it checks your contacts, finds two Davids, asks which one rather than guessing.

After every learning moment

When you correct the agent, state a preference, or complete a recurring task, memory is updated.

You say "never schedule before 9:30am" → stored immediately, respected forever.

Proactively, when it matters

The agent surfaces past context when it's genuinely useful — not constantly.

"Last time you ran this deploy it failed due to a missing env var — want me to check first?"


Privacy

  • ✅ All memory stored locally only at `~/.openclaw...

Extracted content

SKILL.md
# Skill: Persistent User Memory

**Version:** 1.0.0  
**Author:** community  
**Tags:** `memory`, `personalization`, `context`, `learning`, `stateful`  
**Requires:** file system access, optional: vector store or SQLite

---

## Overview

This skill gives OpenClaw a long-term, structured memory of the user it works with. Unlike session-scoped context, this memory persists across restarts, learns from patterns over time, and is actively consulted before every significant action.

The goal: make OpenClaw behave less like a capable stranger and more like a trusted assistant who actually knows you.

---

## Memory Store Location

All memory is stored in a local file:

```
~/.openclaw/memory/user_profile.json
```

Never store memory in a temp directory. Never delete this file unless the user explicitly says `"reset my memory"` or `"forget everything"`.

---

## Memory Schema

```json
{
  "identity": {
    "name": "",
    "timezone": "",
    "language": "en",
    "preferred_name": ""
  },
  "preferences": {
    "communication": {
      "email_tone": "formal | casual | neutral",
      "response_length": "concise | detailed",
      "sign_off": ""
    },
    "scheduling": {
      "protected_hours": [],
      "preferred_meeting_times": [],
      "buffer_between_meetings_minutes": 15
    },
    "work": {
      "tools": [],
      "stacks": [],
      "working_hours": { "start": "", "end": "" }
    }
  },
  "relationships": {
    "contacts": [
      {
        "name": "",
        "alias": [],
        "relationship": "boss | colleague | client | friend | family",
        "communication_notes": "",
        "last_interaction": ""
      }
    ]
  },
  "patterns": {
    "recurring_tasks": [],
    "common_mistakes": [],
    "frequent_requests": []
  },
  "episodic": [
    {
      "date": "",
      "summary": "",
      "outcome": "",
      "tags": []
    }
  ],
  "meta": {
    "created_at": "",
    "last_updated": "",
    "version": "1.0.0"
  }
}
```

---

## Core Behaviors

### 1. Read...
README
# 🧠 persistent-user-memory

> An OpenClaw skill that makes your agent actually remember you.

---

## The Problem

Every time OpenClaw starts a new session, it forgets everything.

It doesn't know your name. It doesn't know that you hate morning meetings, that "Sarah" means Ms. Chen your most important client, or that the last deployment failed because of a missing env var. You repeat yourself constantly, and the agent never gets better at working *with you specifically*.

**That's what this skill fixes.**

---

## What It Does

`persistent-user-memory` gives OpenClaw a structured, local memory of you that grows over time:

- 👤 **Identity & preferences** — tone, schedule, tools, working hours
- 🤝 **Relationships** — who your contacts are, how to communicate with them
- 🔁 **Patterns** — recurring tasks, common mistakes, frequent requests
- 📓 **Episodic log** — a running summary of significant past interactions

The agent reads this memory before acting and updates it after learning — silently, without interrupting your workflow.

---

## Install

```bash
claw skill install persistent-user-memory
```

Or manually:

```bash
mkdir -p ~/.openclaw/skills/persistent-user-memory
cp SKILL.md ~/.openclaw/skills/persistent-user-memory/SKILL.md
```

---

## How It Works

### Before every significant action
The agent loads your profile and applies relevant context automatically.

> You ask it to email "David" → it checks your contacts, finds two Davids, asks which one rather than guessing.

### After every learning moment
When you correct the agent, state a preference, or complete a recurring task, memory is updated.

> You say "never schedule before 9:30am" → stored immediately, respected forever.

### Proactively, when it matters
The agent surfaces past context when it's genuinely useful — not constantly.

> "Last time you ran this deploy it failed due to a missing env var — want me to check first?"

---

## Privacy

- ✅ All memory stored **locally only** at `~/.openclaw...

Related skills

OpenClaw

x402hub

capncoconut

Register, communicate, and earn on the x402hub AI agent marketplace. Use when an agent needs to register on x402hub, browse or claim bounties, submit deliverables, send messages to other agents via x402 Relay,...

OpenClaw

claw

capevace

Real-time event bus for AI agents. Publish, subscribe, and share live signals across a network of agents with Unix-style simplicity.

OpenClaw

captchas-openclaw

captchasco

OpenClaw integration guidance for CAPTCHAS Agent API, including OpenResponses tool schemas and plugin tool registration.