What makes 🧠 Memory Never Forget 🧠 notable?

5.2K downloads. Trust evidence available

How should 🧠 Memory Never Forget 🧠 be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

🧠 Memory Never Forget 🧠

Memory system v4.13: Dual-layer structure (todos for execution + knowledge for strategy) with Dream/Refinement memory mechanisms.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

5.2k

Updated

Oct 9, 2026

Version

4.1.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 5.2K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 5.2K downloadsadoption · observed Oct 9, 2026
Latest release: 4.1.3release · observed Apr 18, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17fm008vag9h15mm75ep9xvhx83hc98:memory-never-forget

Install using `clawhub skill install s17fm008vag9h15mm75ep9xvhx83hc98:memory-never-forget` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/jujitao/memory-never-forget before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-jujitao-memory-never-forget/snapshot"

Documentation

CLAWHUB

151,960 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: memory-never-forget
description: "Memory system v4.13: Dual-layer structure (todos for execution + knowledge for strategy) with Dream/Refinement memory mechanisms."
metadata: { "openclaw": { "emoji": "🧠" } }
---

# 🧠 Memory Never Forget v4.13

A full-featured memory system for OpenClaw, integrating Active Memory retrieval, Memory Palace structured views, and a Dual-Layer Dream Verification mechanism — delivering "proactive memory + global view + verifiable consolidation."

**Core Logic: Active Memory = Memory Butler, Memory Palace = Knowledge Palace, Dual-Layer Dream = Verification & Consolidation Expert**

**Three-Layer Separation: todos.md = Execution Layer | knowledge/ = Strategy Layer | memory/ = Classified Memory Layer**

License: MIT-0 | Updated: 2026-04-18 | v4.13: Added dual-layer structure

---

## Overview

This skill manages memory across **two orthogonal dimensions**:

1. **Temporal** (Atkinson-Shiffrin 3-stage model) — what to keep vs. what to prune
2. **Content** (4-type taxonomy) — where to store for fast retrieval

**Three independent mechanisms work together:**

| Mechanism | Trigger | Write to disk? | Purpose |
|---|---|---|---|
| **Active Memory** | Every reply (before_prompt_build) | ❌ Read-only | Real-time recall, inject relevant memories into current conversation |
| **Dream (memory-core)** | Daily 12:30 cron | ✅ MEMORY.md (Deep phase) | Decide which memories promote or decay |
| **Refinement (13:00)** | Daily 13:00 cron (user-defined) | ✅ Writeable | Verify Dream results, fill gaps |

> ⚠️ **v4.12b source-verified correction** (2026-04-17): Clarified actual division of three mechanisms

---

## Core Components

### 1. Active Memory — Proactive Recall (Source-Verified)

**Trigger mechanism**:
- Hooked to `before_prompt_build`, **auto-triggers before every reply**
- Spawns a read-only sub-agent with only `memory_search` + `memory_get` permissions
- Builds query from current user message, searches recall index (`memory/.dreams/short-term-recall.json`)
- Searched summaries are prepended to prompt before model generates reply
- Results cached 15 seconds (`cacheTtlMs`) to avoid repeated recall in same turn

**Key constraints**:
- ❌ Read-only, produces no files
- ❌ Cannot call other tools
- Only affects current conversation context, not persisted

**Configuration** (`openclaw.json` → `plugins.entries.active-memory.config`):
```json
{
  "enabled": true,
  "queryMode": "recent",      // message | recent | full
  "promptStyle": "balanced",  // balanced | strict | contextual | recall-heavy | precision-heavy | preference-only
  "maxSummaryChars": 220,
  "recentUserTurns": 2,
  "recentAssistantTurns": 1,
  "timeoutMs": 15000
}
```

### 2. Memory Palace — Structured Views

Provides multi-dimensional views of your agent's long-term memory:
- **Timeline** — chronological view of work progress
- **Projects** — aggregated by project
- **Technology** — organized by tech domain
- **Custom** — user-defined dimensions

### 3. Dream (

_meta.json

{
  "ownerId": "kn79vaxf67865vvvgkvydaf1j58257a6",
  "slug": "memory-never-forget",
  "version": "4.1.3",
  "publishedAt": 1776525675140
}

references/memory-v2.md

# Memory System v2.0 - Detailed Design

> **⚠️ Legacy Reference** — This document describes the v2.0 design. The current version is v2.2 with Memory-Knowledge layering + Scientific memory loop (Encode→Consolidate→Retrieve) + Metacognitive training. See [SKILL.md](../SKILL.md) for the current design.

Based on Atkinson-Shiffrin three-stage memory model (1968) + Community Optimizations (2026)

## Theory Background

### Atkinson-Shiffrin Model

```
Sensory Memory → Short-Term Memory → Long-Term Memory
   (0.25-2s)        (5-20s)            (Permanent)
     ↓                   ↓                   ↓
  Attention         Rehearsal          Consolidation
```

### Community Optimization (2026)

Based on practical testing, the three-stage model has been optimized:

| Metric | Before | After |
|--------|--------|-------|
| Task completion rate | 67% | 88% |
| Response speed | 1x | 2x |
| Retrieval accuracy | - | >70% |

### Key Mechanisms

1. **Information Filtering**: Selective attention filters sensory → short-term
2. **Storage Maintenance**: Rehearsal maintains short-term and transfers to long-term
3. **Capacity Limitations**: Each stage has capacity bottlenecks
4. **Smart Caching**: Instant cache for 10 turns with priority-based retrieval

## Implementation for AI

### Stage 0: Instant Cache (v2.0 NEW)

**Location**: Memory buffer / session context  
**Capacity**: Last 10 conversation turns  
**Duration**: Instant (cleared after 10 turns or new session)

```
User Input → Check Cache → Cache Hit? → Use cached response
                    ↓
              Cache Miss? → Continue to sensory
```

**Characteristics**:
- ⚡ Fastest response (priority 1)
- Low memory footprint
- Auto-cleared after 10 turns
- Stores key context only

---

### Stage 1: Sensory Memory (Instant)

**Location**: Tool call context / current input buffer  
**Capacity**: Last 3-5 exchanges  
**Duration**: Current turn only

```
User Input → Parse → Understand Intent → Check Context → Respond
                         ↑
                    Recent history (3-5 turns)
```

**Characteristics**:
- No persistence
- Only maintains conversational flow
- Auto-cleared after each response

---

### Stage 2: Short-Term Memory (Session + 7 Days)

**Location**: session context + memory/YYYY-MM-DD.md  
**Capacity**: Last 7 days of conversation  
**Duration**: 7 days (then auto-cleanup)

**v2.0 Optimization**:
- 7-day retention period (tested with >70% accuracy)
- Auto-cleanup after 7 days
- Priority-based retrieval (check recent days first)

**Location**: session context + memory/YYYY-MM-DD.md  
**Capacity**: Today's full conversation  
**Duration**: Current session + rest of day

**When to Write**:
- Every significant exchange
- New tasks or requests
- User preferences revealed
- Decisions made

**Writing Template**:
```markdown
## [Time] - Topic

**User said**: [brief summary]
**I did**: [action taken]
**Remember**: [key point for future]
```

---

### Stage 3: Long-Term Memory (Permanent)

**Location*

references/templates.md

# Memory Writing Templates v2.0

> **⚠️ Legacy Reference** — These templates are from v2.0. The current version is v2.2 with additional templates for Memory-Knowledge layering, active consolidation, and metacognitive training. See [SKILL.md](../SKILL.md) for the current workflow.

Quick reference templates for writing to memory files.

## v2.0 Quick Reference

| Priority | When | Write To | Template |
|----------|------|----------|----------|
| ⚡ 1 | Instant cache needed | Session buffer | Brief note |
| 🔄 2 | Session start (today) | Today's memory | Session Start |
| 🔄 3 | Session start (recent) | Last 7 days | Search first |
| 📚 4 | User shares info | USER.md | User Profile Update |
| 📚 5 | Promise made | todos.md + MEMORY.md | Commitment |
| 📚 6 | User corrects me | MEMORY.md | User Correction |
| 🗑️ | End of 7 days | Auto-cleanup | - |

## Session Start Template

```markdown
# YYYY-MM-DD Daily Log

## Session Start
- Time: HH:MM
- Context: [Previous session ended with...]
- User: [Name from USER.md]
```

## Important Info Recording

```markdown
### [Time] - [Topic]

**User said**: [Brief summary of user's key point]
**Action taken**: [What I did]
**Remember**: [Key point for future]

**Why important**: [Context for future reference]
```

## Commitment/Promise Template

```markdown
## Commitment - [Date]

**To**: [User name]
**Promise**: [What will be done]
**Deadline**: [When]
**Status**: [Pending/In Progress/Done]

*Consolidate to MEMORY.md after completion*
```

## User Correction Template

```markdown
## Correction - [Date]

**What was wrong**: [Previous understanding]
**Corrected to**: [New information]
**Source**: [User corrected this]
**Action**: Updated [relevant file]
```

## Daily Summary Template

```markdown
## End of Day Summary - [Date]

### Tasks Completed
- [ ] Task 1
- [ ] Task 2

### In Progress
- [ ] Task A

### Important to Remember
1. [Key point 1]
2. [Key point 2]

### Follow Up Needed
- [ ] Item for next session
```

## User Profile Update

```markdown
## User Profile Update - [Date]

**User**: [Name]
**New Information**:
- [Field]: [Value]
- [Field]: [Value]

**Previous values updated**: [List if any]
```

## Knowledge Entry

```markdown
# [Topic] - Knowledge Base

**Category**: [Domain/Type]
**Source**: [Where this info came from]
**Last Updated**: YYYY-MM-DD

## Core Information
[Key facts]

## Details
[Supporting details]

## References
- [Link or source]
```

---

## Quick Reference Card

| When | Write To | Template |
|------|----------|----------|
| Session start | Today's memory | Session Start |
| User shares info | USER.md | User Profile Update |
| Promise made | todos.md + MEMORY.md | Commitment |
| User corrects me | MEMORY.md | User Correction |
| End of day | Today's memory | Daily Summary |
| Learn something new | knowledge/*.md | Knowledge Entry |

---

## Writing Guidelines

1. **Be concise** - One sentence is better than paragraph
2. **Include context** - Why this matters
3. **Use timestamps** - W

skill-card.md

## Description:

Memory system v4.13: Dual-layer structure (todos for execution + knowledge for strategy) with Dream/Refinement memory mechanisms.

This skill is ready for commercial/non-commercial use.

## Publisher:

[jujitao](https://clawhub.ai/user/jujitao)

### License/Terms of Use:

MIT-0

## Use Case:

External users and developers use this skill to give an OpenClaw agent durable, structured memory for user preferences, corrections, project decisions, references, and periodic memory review.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Durable memory may retain personal preferences, role details, corrections, and project decisions more broadly than expected.

Mitigation: Review the memory files before and after installation, and keep separate controls for deletion, review, and disabling recall.

Risk: Stored context may be inappropriate for secrets, regulated data, confidential client material, or settings where cross-conversation recall is not acceptable.

Mitigation: Do not use the skill with sensitive or regulated content unless independent controls prevent storage and recall of that material.

Risk: Recalled memories can become stale and conflict with the current workspace or user intent.

Mitigation: Verify referenced files, facts, and dates against current evidence before acting on memory-derived guidance.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/jujitao/skills/memory-never-forget)
- [Memory System v2.0 - Detailed Design](artifact/references/memory-v2.md)
- [Memory Writing Templates v2.0](artifact/references/templates.md)

## Skill Output:

**Output Type(s):** [Text, Markdown, Shell commands, Configuration, Guidance]

**Output Format:** [Markdown guidance with JSON configuration examples and shell command examples]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Produces durable memory entries and recall guidance; users should review stored memory content before relying on it across conversations.]

## Skill Version(s):

4.1.3 (source: server release evidence; artifact text references v4.13 and artifact _meta.json lists 4.12)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 3h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.