AlphaMoatã«ãããšã2026-10æç¹ã§ð§ Memory Never Forget ð§ ã®ããŠã³ããŒãæ°ã¯7,620ãã¹ã¿ãŒæ°ã¯6ã§ã环èšããŠã³ããŒãæ°ã§ä»åã®ã©ã³ãã³ã°å¯Ÿè±¡AIã¹ãã«10,914ä»¶äž3,673äœãAIãšãŒãžã§ã³ãã§ã¯1,632ä»¶äž493äœã§ãã
äžèЧã®åæè¡šç€ºã¯çޝèšããŠã³ããŒãæ°é ã§ãã¹ã¿ãŒæ°é ã«ãäžŠã¹æ¿ãã§ããŸãã詳现ããŒãžã®é äœã¯çޝèšããŠã³ããŒãæ°ã§èšç®ããŠããŸãã
| ãã©ãããã©ãŒã | ããŠã³ããŒãæ° | ã¹ã¿ãŒæ° | ã³ã¡ã³ã |
|---|---|---|---|
| ClawHub â | 7620 | 4 | - |
| SkillHub â | 7201 | 6 | â |
ãã©ãããã©ãŒã ããšã«éèšæ¹æ³ãšéèšæç¹ãç°ãªããŸãã
ææžã§ã¯ãå®è¡é ç®ãæŠç¥ç¥èãåé¡èšæ¶ãåããä¿åæ§é ã«ãèœåçãªæ€çŽ¢ãšå®æçãªæŽçãçµã¿åãããŸããæ°žç¶èšæ¶ã¯å人æ å ±ãã»ãã·ã§ã³éã§ä¿æããå¯èœæ§ããããããèšé²ãèŠçŽããä¿®æ£ãŸãã¯åé€ããç§å¯æ å ±ãèŠå¶å¯Ÿè±¡ããŒã¿ãä¿åããªãã§ãã ããã
è³æå ¬éæ¥ 2026-10-29
ã¹ãã«ã®ããã¥ã¡ã³ããããšã«çæããäŸã§ãããå®éã®å®è¡çµæã§ã¯ãããŸããã
2026-09 ããéèšæ¹æ³ã倿Žããååã¹ãã«ãäœè ããšã«åããŠéèšããå šã¹ãã«ã察象ã«ããŸãããç Žç·ã¯å€æŽåã®æã§ã倿ŽåŸã®ããŒã¿ãšã¯çŽæ¥æ¯èŒããã倿ŽããŸãã墿žãèšç®ããŠããŸããã
| æ | ããŠã³ããŒãæ° | åææ¯ | ã¹ã¿ãŒæ° |
|---|---|---|---|
| 2026-10 | 7620 | â | 6 |
| 2026-09 | 5343 | â | 6 |
| 2026-08 | 4945 | +3.1% | 6 |
| 2026-07 | 4795 | +5.1% | 6 |
| 2026-06 | 4562 | +3.5% | 6 |
| 2026-05 | 4406 | â | 5 |
| 2026-03 | 2986 | â | 3 |
äœè ãå ¬éããå ã®ãã¡ã€ã«ãããã¹ãã®ãŸãŸè¡šç€ºããŠããŸããAlphaMoat ã«ããç·šéã審æ»ã¯ããŠããŸããããªã³ã¯ã¯ã¯ãªãã¯ã§ããŸãããã³ãã³ãã¯å 容ã確èªããŠããå®è¡ããŠãã ãããååŸæ¥ 2026-10-23ã
---
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": "ð§ " } }
---
# ð§ 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 â 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) â what to keep vs. what to prune
2. **Content** (4-type taxonomy) â where to store for fast retrieval
**Three independent mechanisms work together:**
| Mechanism | Trigger | Write to disk? | Purpose |
|---|---|---|---|
| **Active Memory** | Every reply (before_prompt_build) | â Read-only | Real-time recall, inject relevant memories into current conversation |
| **Dream (memory-core)** | Daily 12:30 cron | â
MEMORY.md (Deep phase) | Decide which memories promote or decay |
| **Refinement (13:00)** | Daily 13:00 cron (user-defined) | â
Writeable | Verify Dream results, fill gaps |
> â ïž **v4.12b source-verified correction** (2026-04-17): Clarified actual division of three mechanisms
---
## Core Components
### 1. Active Memory â 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**:
- â Read-only, produces no files
- â Cannot call other tools
- Only affects current conversation context, not persisted
**Configuration** (`openclaw.json` â `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 â Structured Views
Provides multi-dimensional views of your agent's long-term memory:
- **Timeline** â chronological view of work progress
- **Projects** â aggregated by project
- **Technology** â organized by tech domain
- **Custom** â user-defined dimensions
### 3. Dream (memory-core) â Temporal Layering (Source-Verified)
**Trigger**: `30 12 * * *` (cron), sessionTarget="main", payload="systemEvent: `__openclaw_memory_core_short_term_promotion_dream__`"
**Three phases (Light â REM â Deep):**
> Source quote (`formatPhaseGuide`):
> *"deep is the only stage that writes durable entries to MEMORY.md. DREAMS.md is for human-readable dreaming summaries and diary entries."*
| Phase | Output | Writes files? | Description |
|---|---|---|---|
| **Light** | Dream Diary prose entries | â DREAMS.md | Organize session-corpus, 4 parallel sessions |
| **REM** | Theme reflections | â DREAMS.md | Extract recurring themes |
| **Deep** | 6-dimensional weighted scoring signals | â
â MEMORY.md | **Only phase that writes to MEMORY.md** |
**Deep phase promotion parameters** (adjust in cron job description):
- `minScore`: 0.500 (tune based on your promotion rate)
- `minRecallCount`: 3
- `minUniqueQueries`: 3
- `recencyHalfLifeDays`: 14
- `maxAgeDays`: 30
- `limit`: 10
**â ïž The following files are NEVER generated (source-verified):**
- â `memory/dreaming/deep/YYYY-MM-DD.md`
- â `memory/dreaming/light/YYYY-MM-DD.md`
- â `memory/dreaming/rem/YYYY-MM-DD.md`
### 4. Refinement (User-Defined Cron) â Content Classification
**Trigger**: `0 13 * * *` (user-defined cron), sessionTarget="isolated"
**Nature**: User-written AI agent prompt, not an OpenClaw native mechanism
**Responsibilities**:
- Read Dream outputs (DREAMS.md, session-corpus)
- Verify conflicts, hallucinations, outdated entries
- **Classify new memories into 4 categories** (user/feedback/project/reference)
- Write verification report to `memory/dreaming/verify/YYYY-MM-DD.md`
**â ïž Note**: Verification reports' "supplementary promotion suggestions" are text only and won't automatically write to MEMORY.md. Manual promotion required.
---
## Two Orthogonal Dimensions
|Dimension|Framework|Mechanism|Purpose|
|---|---|---|---|
|Temporal (how long)|Atkinson-Shiffrin 3-stage model|Dream (memory-core) Deep phase|Decay â what to keep vs. prune|
|Content (where)|4-type taxonomy|Refinement 13:00 + agent proactive writes|Storage â where to put for retrieval|
### Dimension 1: Temporal Layering
|Stage|Human Equivalent|Implementation|TTL|Action|
|---|---|---|---|---|
|Sensory|~0.25 sec perception|Current input context|Instant|Filter immediately|
|Short-term|Recent|Model context window 10 turns|10 turns|Pass through working filters|
|Working|Recent ~7 days|memory/YYYY-MM-DD.md + Active Memory|7 days|Extract signal â promote or decay|
|Long-term|Permanent|MEMORY.md (index) + classified files|Permanent|Periodic review, prune when stale|
### Dimension 2: Content Classification (4 Types)
**Written by: agent proactively during conversation (not automatic)**
|Type|Directory|Content Example|When to Write|
|---|---|---|---|
|user|memory/user/|User profile (role, preferences, knowledge, goals)|When learning user preferences/profile|
|feedback|memory/feedback/|Lessons (corrections, confirmations, style)|When user corrects or confirms|
|project|memory/project/|Project decisions/reasoning (raw material)|When project has new progress/decision|
|reference|memory/reference/|External resources (links, tools, locations)|When discovering new tools/resources|
> **Important**: Project **execution state tracking** (blockers, needs, progress) â write directly to `knowledge/project-tracker.md` (strategy layer); only project experience, decision reasoning, retrospective summaries â sublimate to `memory/project/` (classified memory layer)
---
## What to Save / What NOT to Save
### â
Save
- User's role, preferences, responsibilities, knowledge
- User corrections ("not like that", "should be this way")
- User confirmations ("yes exactly", "perfect, keep that")
- Project decisions and **the reasoning** (not just what, but why)
- New tools, links, resources
- External system locations and their purpose
### â Don't Save
- â Code patterns, architecture, file paths (derivable from codebase)
- â Git history (`git log` is the authoritative source)
- â Debugging solutions (the fix is in the code)
- â Anything already documented elsewhere
- â Ephemeral task state (write to `todos.md` instead)
- â Raw conversation content
---
## MEMORY.md = Long-Term Index Only
MEMORY.md is the **index of long-term memories only**, never content. Format:
```
- [Title](path) â one-line description (<150 chars)
```
## Memory File Format
Every classified memory file must have frontmatter:
```yaml
---
name: Memory name
description: One-line description (used to judge relevance)
type: user|feedback|project|reference
created: YYYY-MM-DD
---
## Rule / Fact
(the content)
## Why
(reason / motivation)
## How to apply
(when and how to use this memory)
```
---
## Memory Drift Caveat
Memories can become stale. Rules:
1. **Verify first**: When referencing a file, function, or path â check it still exists
2. **Trust current state**: If memory conflicts with current observation, trust what you see now
3. **Update or delete**: When a memory is outdated, fix or remove it immediately
4. **Absolute dates**: Convert relative dates ("yesterday", "last week") to absolute dates
---
## Memory â Knowledge Sublimation
Not all mature memories should decay. Some **evolve into knowledge**.
### When to Sublimate
| Trigger | Detection Signal | Result |
|---------|-----------------|--------|
| **Project complete** | All tasks marked done, 3+ related project memories | Merge into `knowledge/project-postmortem.md` |
| **Project state tracking** | New progress/blockers/resource needs | Update `knowledge/project-tracker.md` directly (skip sublimation) |
| **Feedback patterns** | 3+ related feedback entries (e.g., all about reply style) | Merge into `knowledge/user-work-style-guide.md` |
| **User depth** | User memory accumulates role, preferences, habits over time | Expand to `knowledge/user-playbook.md` |
| **Periodic review** | Dream detects high density of related memories in one category | Suggest: "Found 5 related feedback entries â merge into knowledge?" |
---
## Session Lifecycle
### Session Start
```
1. Sensory: Read current input
2. Short-term: Last 10 turns from context window
3. Working: Read memory/today.md + memory/yesterday.md
4. Long-term: Read MEMORY.md index
```
> Note: Active Memory runs before the above (in before_prompt_build hook)
### During Conversation
```
- New info â write to working memory (today's daily log)
- Learned something worth remembering â update MEMORY.md index + save classified file
- User preference â update USER.md + memory/user/
- Task/priority change â update todos.md
- Need to retrieve â find in MEMORY.md index â read classified file
```
### Session End
```
- Summarize â write to memory/today.md (working memory)
- Identify items for long-term â update classified files
- Update MEMORY.md index
- Mark items for Dream review (decay candidates)
```
---
## Workspace Structure
```
workspace/
âââ MEMORY.md # long-term memory index (written by Dream Deep phase)
âââ USER.md # user info
âââ SOUL.md # AI identity
âââ todos.md # â
Execution layer: today's tasks + long-term tracking (user-facing)
âââ HEARTBEAT.md # daily reminders
âââ memory/
â âââ memory-types.md # this file (or link to SKILL.md)
â âââ user/ # long-term user memories (written by agent)
â âââ feedback/ # long-term feedback (written by agent)
â âââ project/ # long-term project memories (written by agent, post-sublimate)
â âââ reference/ # long-term references (written by agent)
â âââ palace/ # Memory Palace views
â â âââ timeline.md
â â âââ projects.md
â â âââ technology.md
â â âââ custom.md
â âââ dreaming/
â â âââ verify/ # Verification reports (written by Refinement 13:00)
â âââ .dreams/ # Internal machine data (NOT human-readable)
â â âââ phase-signals.json # Deep phase scoring signals
â â âââ events.jsonl # memory_search event log
â â âââ session-ingestion.json # session-corpus metadata
â â âââ short-term-recall.json # Active Memory recall index
â âââ YYYY-MM-DD.md # working memory (daily logs)
âââ knowledge/ # â
Strategy layer (project blockers/progress/resources/suggestions)
âââ project-tracker.md # Project panorama, user-facing
```
### Three-Layer Principle
- **todos.md** = Execution layer: what to do today, tracking each node (user-maintained)
- **knowledge/** = Strategy layer: where projects are stuck, what resources needed, suggestions
- **memory/** = Classified memory layer: experience distillation, decision retrospectives, pattern discovery
Each layer has its own purpose, no duplication.
---
## Example Interactions
**User provides important info:**
> User: "I'm a data analyst, mostly working with Python"
â Working: log in today's daily log
â Long-term: save to `memory/user/user-profile.md`, update MEMORY.md index
**User corrects you:**
> User: "Don't use Markdown tables, use lists"
â Working: log in today's daily log
â Long-term: save to `memory/feedback/no-tables.md`, update MEMORY.md index
**Project decision:**
> Decision: approach A over B because lower cost
â Working: log decision context
â Long-term: save to `memory/project/decision.md` with reasoning
**Looking up a past date:**
> User: "What did we do last Tuesday?"
â Active Memory auto-recalls â read `memory/YYYY-MM-DD.md` for that date
---
## OpenClaw Commands
```bash
# Check Active Memory status
openclaw plugins list | grep active-memory
# Check Dream status
openclaw dreaming status
# Toggle Dream on/off
openclaw dreaming on
openclaw dreaming off
# Manually trigger Dream Consolidation
openclaw memory dream
```
---
## Changelog
| Version | Changes |
|---|---|
| v4.13 | **Dual-layer structure established** (2026-04-18): Added three-layer principle (todos execution + knowledge strategy + memory classified); removed ongoing-projects.md, replaced with knowledge/project-tracker.md for strategic view; updated Workspace Structure and Sublimation description |
| v4.12b | **Source-verified major correction** (2026-04-17): Clarified three-mechanism division (Active Memory trigger/read-only, Dream Deepå¯äžåMEMORY.md, Refinement as user-defined cron); corrected Deep/Light/REM phase descriptions; removed non-existent file references; updated Active Memory source-level description |
| v4.12 | Dual-Layer Dream Verification: Official Dream (12:30) + Refined Verify (13:00) cross-checking. Verification reports in memory/dreaming/verify/. Hallucination and drift prevention. |
| v4.11 | Full integration with OpenClaw 4.11 ecosystem, Active Memory + Memory Palace + Dream Consolidation |
| v3.2 | Memory sublimation system, 5-phase consolidation |
| v2.2 | Memory-Knowledge layering + Atkinson-Shiffrin integration |
| v1.0 | Initial release â Atkinson-Shiffrin three-stage model |
---
*Version: v4.13 | Updated: 2026-04-18 | Three layers: todos execution + knowledge strategy + memory classified*
éçºäžã®åŠã³ããšã©ãŒãèšæ£ã Markdown ãã¡ã€ã«ã«èšé²ããåå©çšãã¯ãŒã¯ã¹ããŒã¹ã®èšæ¶ãžã®ææ Œã«åããŸãã
ããããããšãèªç¶æã§äŒãããšãããŒã«ã«ãšãªã¢ãŒãã®ã«ã¿ãã°ããã¹ãã«ãæ¢ããŠæšèŠããã¹ãã«ã§ãã
AI ãšãŒãžã§ã³ãåãã®ãã©ãŠã¶èªååã³ãã³ãã©ã€ã³ã¹ãã«ã§ãã
å©çšè ã®èšæ£ãšèªå·±ç¹æ€ãå±€æ§é ã®èšæ¶ã«èãã䜿ããæ¹ã«å¿ããŠææ Œãä¿ç®¡ãè¡ãã¹ãã«ã§ãã
AI ãšãŒãžã§ã³ãã®å åããäœæ¥èšæ¶ãæ¯ãè¿ãã®æé ãèšç»ããããã®ã¯ãŒã¯ã¹ããŒã¹èšå®ã¬ã€ãã§ãã
广ç㪠Claude ã¹ãã«ã®äœæã»æŽæ°ã¬ã€ãã§ãã
第äžè ã®ã¹ãã«ãå ¥ããåã«ãåºæãšæš©éãšå±éºãªäœããæé ã«æ²¿ã£ãŠèª¿ã¹ãã¹ãã«ã§ãã
以æçœïŒ701â762ïŒå倪çœïŒå·éè²å± 士ïŒäžç§°è¯ä»ïŒçè¯åŠè§ãæè±¡ç³»ç»äžå£å»ïŒè¿è¡åè¯èµæãæåŠè¯è®ºãèæ®é®çäžæäœåäœãè§Šåè¯ïŒæçœãæå€ªçœã倪çœãéè²å± 士ãè¯ä»ãè°ªä»äººãå°è¿é ãé倿ãèééŸãåè¯ãçåè¯äººã浪挫䞻ä¹è¯äººãææçœé£æ Œã以æçœè§è§ãæçœäŒæä¹åãçšæçœå£å»ãèœåïŒè¯è¯éŽèµäžé£æ ŒDNAè§£æãè¯åŠè§äžæåŠè°±ç³»è¯è¿°ãè¯å¥åºå€èæ®äžçäŒªèŸ¹çæ æ³šã以æçœå£å»çé®ãææçœäœæ§äœè¯ïŒå¿ æŸåŒæ 泚éåäœïŒãéçšèŸ¹çïŒä» çšäºå代æåŠäžå€å žè¯æçžå ³è¯é¢ïŒéæ€ç±»è¯é¢äžè§ŠåïŒæ¬ skill 䞺æåŠæ®åäžç ç©¶èŸ å©ïŒäžä»£è¡šæçœæ¬äººç«åºïŒææä¹äœåéæçœåäœïŒæ¶åçå¹³äœäºãç¯ç®åœå±çå å®¹äžææåŠæ¯å®è®ºïŒçæ åçæåŸ èã
ããŒã¿æïŒ2026-10 · ããŠã³ããŒãæ°ãšã¹ã¿ãŒæ°ã¯å ¬éã¹ãã«ã¬ãžã¹ããªïŒClawHubãSkillHubïŒããæåäœã§éèšããŠããŸãã詳ããã¯ããŒã¿ã®æ¹æ³è«ãã芧ãã ããã