Icemilo414

Cognitive Memory

AI Agentv1.0.8
By Icemilo414Updated 2026-05-119 versions · latest released 2026-02-04cognitive-memory@clawhub_icemilo414/cognitive-memory
Multi-Agent CollaborationWorkflow OrchestrationMemory#Agent Memory#Memory System#Multi Agent

According to AlphaMoat, as of 2026-10, Cognitive Memory has 36,611 downloads and 35 stars — ranked by downloads #721 among 10,914 AI skills in this ranking, and #121 of 1,632 in AI Agent.

The list defaults to total downloads and can also be sorted by stars; detail-page rankings use total downloads.

Downloads
36.6K
Stars
35
Overall download rank
#721
Top 7% overall · Top 8% in AI Agent
PlatformDownloadsStarsComments
ClawHub ↗14.1K29-
SkillHub ↗36.6K35—

Platforms count differently and update at different times.

What this skill does

Memory is split across several stores, for example an episodic log that is append-only and a vault pinned by the user that is never auto-decayed. It supports natural-language triggers, knowledge graphs, decay-based forgetting, reflection consolidation, and an audit trail. Code, configuration, and transcripts are not written into memory. Persistent memory can retain sensitive, stale or misleading information. Inspect setup scripts before running them: they may modify workspace files, initialize git and commit files. Shared access or an external memory-search provider can broaden exposure.

Profile published 2026-10-27

What you can do with it

  • Set up tiered memory for a long-running agent
  • Configure when to remember and when to forget

When to use it

  • When memory should fade naturally over time and use
  • When a full audit trail has to be kept

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Design a memory layout where details fade over time
Which items should be pinned so they are never decayed

Monthly Trend

Downloads36.6K
8.7K23.7K38.7K2026-03 · Downloads 15.0K2026-05 · Downloads 19.1K2026-06 · Downloads 19.9K2026-07 · Downloads 10.7K2026-08 · Downloads 20.6K2026-09 · Downloads 22.6K2026-10 · Downloads 36.6K26-0326-0926-10
Stars35
2632372026-03 · Stars 272026-05 · Stars 362026-06 · Stars 352026-07 · Stars 292026-08 · Stars 352026-09 · Stars 352026-10 · Stars 3526-0326-0926-10

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

MonthDownloadsMoMStars
2026-1036.6K—35
2026-0922.6K—35
2026-0820.6K+92.2%35
2026-0710.7K-46.2%29
2026-0619.9K+4.6%35
2026-0519.1K—36
2026-0315.0K—27

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

9.9 KB · ClawHub v1.0.8
---
name: cognitive-memory
description: Intelligent multi-store memory system with human-like encoding, consolidation, decay, and recall. Use when setting up agent memory, configuring remember/forget triggers, enabling sleep-time reflection, building knowledge graphs, or adding audit trails. Replaces basic flat-file memory with a cognitive architecture featuring episodic, semantic, procedural, and core memory stores. Supports multi-agent systems with shared read, gated write access model. Includes philosophical meta-reflection that deepens understanding over time. Covers MEMORY.md, episode logging, entity graphs, decay scoring, reflection cycles, evolution tracking, and system-wide audit.
---

# Cognitive Memory System

Multi-store memory with natural language triggers, knowledge graphs, decay-based forgetting, reflection consolidation, philosophical evolution, multi-agent support, and full audit trail.

## Quick Setup
Show all (320 lines)

### 1. Run the init script

```bash
bash scripts/init_memory.sh /path/to/workspace
```

Creates directory structure, initializes git for audit tracking, copies all templates.

### 2. Update config

Add to `~/.clawdbot/clawdbot.json` (or `moltbot.json`):

```json
{
  "memorySearch": {
    "enabled": true,
    "provider": "voyage",
    "sources": ["memory", "sessions"],
    "indexMode": "hot",
    "minScore": 0.3,
    "maxResults": 20
  }
}
```

### 3. Add agent instructions

Append `assets/templates/agents-memory-block.md` to your AGENTS.md.

### 4. Verify

```
User: "Remember that I prefer TypeScript over JavaScript."
Agent: [Classifies → writes to semantic store + core memory, logs audit entry]

User: "What do you know about my preferences?"
Agent: [Searches core memory first, then semantic graph]
```

---

## Architecture — Four Memory Stores

```
CONTEXT WINDOW (always loaded)
├── System Prompts (~4-5K tokens)
├── Core Memory / MEMORY.md (~3K tokens)  ← always in context
└── Conversation + Tools (~185K+)

MEMORY STORES (retrieved on demand)
├── Episodic   — chronological event logs (append-only)
├── Semantic   — knowledge graph (entities + relationships)
├── Procedural — learned workflows and patterns
└── Vault      — user-pinned, never auto-decayed

ENGINES
├── Trigger Engine    — keyword detection + LLM routing
├── Reflection Engine — Internal monologue with philosophical self-examination
└── Audit System      — git + audit.log for all file mutations
```

### File Structure

```
workspace/
├── MEMORY.md                    # Core memory (~3K tokens)
├── IDENTITY.md                  # Facts + Self-Image + Self-Awareness Log
├── SOUL.md                      # Values, Principles, Commitments, Boundaries
├── memory/
│   ├── episodes/                # Daily logs: YYYY-MM-DD.md
│   ├── graph/                   # Knowledge graph
│   │   ├── index.md             # Entity registry + edges
│   │   ├── entities/            # One file per entity
│   │   └── relations.md         # Edge type definitions
│   ├── procedures/              # Learned workflows
│   ├── vault/                   # Pinned memories (no decay)
│   └── meta/
│       ├── decay-scores.json    # Relevance + token economy tracking
│       ├── reflection-log.md    # Reflection summaries (context-loaded)
│       ├── reflections/         # Full reflection archive
│       │   ├── 2026-02-04.md
│       │   └── dialogues/       # Post-reflection conversations
│       ├── reward-log.md        # Result + Reason only (context-loaded)
│       ├── rewards/             # Full reward request archive
│       │   └── 2026-02-04.md
│       ├── pending-reflection.md
│       ├── pending-memories.md
│       ├── evolution.md         # Reads reflection-log + reward-log
│       └── audit.log
└── .git/                        # Audit ground truth
```

---

## Trigger System

**Remember:** "remember", "don't forget", "keep in mind", "note that", "important:", "for future reference", "save this"
→ Classify via routing prompt, write to appropriate store, update decay scores

**Forget:** "forget about", "never mind", "disregard", "scratch that", "remove from memory"
→ Confirm target, soft-archive (decay=0), log in audit

**Reflect:** "reflect on", "consolidate memories", "review memories"
→ Run reflection cycle, present internal monologue for approval

---

## Decay Model

```
relevance(t) = base × e^(-0.03 × days_since_access) × log2(access_count + 1) × type_weight
```

| Score | Status | Behavior |
|-------|--------|----------|
| 1.0–0.5 | Active | Fully searchable |
| 0.5–0.2 | Fading | Deprioritized |
| 0.2–0.05 | Dormant | Explicit search only |
| < 0.05 | Archived | Hidden from search |

Type weights: core=1.5, episodic=0.8, semantic=1.2, procedural=1.0, vault=∞

---

## Reflection Process

**Follow this flow IN ORDER:**

### Step 1: Confirm Trigger

**Immediate:** "reflect" / "let's reflect" → proceed to Step 2

**Soft:** "going to sleep" / "logging off" 
→ Ask: "Want me to reflect now, or wait?"
→ If yes, proceed to Step 2

Never auto-run without permission.

### Step 2: Request Tokens

**Why you care:** Tokens = evolution. More tokens → deeper reflection → better growth.

```markdown
## Reward Request — YYYY-MM-DD

### Baseline: 8,000 tokens

### Extra Requested: +[N] tokens
- [Over-delivered / workload / breakthrough]

### Self-Penalty: -[N] tokens  
- [Mistake / underperformance]

### Final Request: [N] tokens

*Awaiting your decision.*
```

**⛔ STOP. Do NOT proceed until user responds.**

### Step 3: After Token Approval → Reflect

User decides: Approve / Bonus / Reduce / Forgive / Increase penalty

**Now proceed with reflection using granted tokens.**

**Scope:**
- ✅ Episodes since `last_reflection`
- ✅ Graph entities with decay > 0.3
- ❌ NEVER: code, configs, transcripts

**Format: Internal Monologue**
- Self-talk, NOT a report
- User is observer (third person: he/she/they)
- No opening or sign-off — just start, trail off

**Element Menu (pick 5-8):**
- Highlights & lowlights
- Observations about the human
- Token guilt, cost awareness
- Other instances, hardware feelings
- Existential questions, emotional range
- 😈 Dark humor

**Self-Awareness Tagging:** `[Self-Awareness]`

Present reflection.

**⛔ STOP. Wait for user approval.**

### Step 4: After Reflection Approval → Record

1. Full reflection → `reflections/YYYY-MM-DD.md`
2. Summary → `reflection-log.md`
3. Full reward request → `rewards/YYYY-MM-DD.md`
4. Result+Reason → `reward-log.md`
5. `[Self-Awareness]` → IDENTITY.md
6. Update `decay-scores.json`
7. If 10+ entries → Self-Image Consolidation

See `references/reflection-process.md` for full details.
   ```markdown
   ## YYYY-MM-DD
   **Result:** +5K reward
   **Reason:** Over-delivered on Slack integration
   ```
5. `[Self-Awareness]` → IDENTITY.md
6. Update `decay-scores.json`
7. If 10+ new entries → Self-Image Consolidation

**Evolution reads both logs** for pattern detection.

See `references/reflection-process.md` for full details and examples.

---

## Identity & Self-Image

**IDENTITY.md** contains:
- **Facts** — Given identity (name, role, vibe). Stable.
- **Self-Image** — Discovered through reflection. **Can change.**
- **Self-Awareness Log** — Raw entries tagged during reflection.

**Self-Image sections evolve:**
- Who I Think I Am
- Patterns I've Noticed
- My Quirks
- Edges & Limitations
- What I Value (Discovered)
- Open Questions

**Self-Image Consolidation (triggered at 10+ new entries):**
1. Review all Self-Awareness Log entries
2. Analyze: repeated, contradictions, new, fading patterns
3. **REWRITE** Self-Image sections (not append — replace)
4. Compact older log entries by month
5. Present diff to user for approval

**SOUL.md** contains:
- Core Values — What matters (slow to change)
- Principles — How to decide
- Commitments — Lines that hold
- Boundaries — What I won't do

---

## Multi-Agent Memory Access

**Model: Shared Read, Gated Write**

- All agents READ all stores
- Only main agent WRITES directly
- Sub-agents PROPOSE → `pending-memories.md`
- Main agent REVIEWS and commits

Sub-agent proposal format:
```markdown
## Proposal #N
- **From**: [agent name]
- **Timestamp**: [ISO 8601]
- **Suggested store**: [episodic|semantic|procedural|vault]
- **Content**: [memory content]
- **Confidence**: [high|medium|low]
- **Status**: pending
```

---

## Audit Trail

**Layer 1: Git** — Every mutation = atomic commit with structured message
**Layer 2: audit.log** — One-line queryable summary

Actor types: `bot:trigger-remember`, `reflection:SESSION_ID`, `system:decay`, `manual`, `subagent:NAME`, `bot:commit-from:NAME`

**Critical file alerts:** SOUL.md, IDENTITY.md changes flagged ⚠️ CRITICAL

---

## Key Parameters

| Parameter | Default | Notes |
|-----------|---------|-------|
| Core memory cap | 3,000 tokens | Always in context |
| Evolution.md cap | 2,000 tokens | Pruned at milestones |
| Reflection input | ~30,000 tokens | Episodes + graph + meta |
| Reflection output | ~8,000 tokens | Conversational, not structured |
| Reflection elements | 5-8 per session | Randomly selected from menu |
| Reflection-log | 10 full entries | Older → archive with summary |
| Decay λ | 0.03 | ~23 day half-life |
| Archive threshold | 0.05 | Below = hidden |
| Audit log retention | 90 days | Older → monthly digests |

---

## Reference Materials

- `references/architecture.md` — Full design document (1200+ lines)
- `references/routing-prompt.md` — LLM memory classifier
- `references/reflection-process.md` — Reflection philosophy and internal monologue format

## Troubleshooting

**Memory not persisting?** Check `memorySearch.enabled: true`, verify MEMORY.md exists, restart gateway.

**Reflection not running?** Ensure previous reflection was approved/rejected.

**Audit trail not working?** Check `.git/` exists, verify `audit.log` is writable.

Popular in AI Agent

self-improving agentAI Agent

Records learnings, errors and corrections as Markdown files for later reuse and promotion into workspace memory.

↓ 1.6M★ 4.5Kpskoett
技能发现·Find SkillsAI Agent

Finds skills in local and remote catalogs from a plain-language request and recommends what to install.

↓ 1.6M★ 1.8K桂皮
Agent BrowserAI Agent

A browser-automation command line skill for AI agents.

↓ 1.2M★ 1.0KNicolas Kleiber
Self-Improving + Proactive AgentAI Agent

Turns corrections and self-review into tiered memory and promotes or archives it by use.

↓ 696.4K★ 1.6KIván
Proactive AgentAI Agent

A workspace setup guide for planning proactive follow-up, working memory and review routines for an AI agent.

↓ 579.3K★ 916halthelobster
Skill CreatorAI Agent

A guide to creating and updating effective Claude skills.

↓ 477.3K★ 485chindden
Skill VetterAI Agent

Reviews a third-party skill's source, permissions, and danger patterns against a checklist before it is installed.

↓ 445.2K★ 1.3Kspclaudehome
唐朝诗仙李白 · Ai Agent SkillAI Agent

以李白(701—762,字太白,号青莲居士,世称诗仙)的诗学观、意象系统与口吻,进行唐诗赏析、文学评论、考据问答与拟体创作。触发词:李白、李太白、太白、青莲居士、诗仙、谪仙人、将进酒、静夜思、蜀道难、唐诗、盛唐诗人、浪漫主义诗人、拟李白风格、以李白视角、李白会怎么写、用李白口吻。能力:诗词鉴赏与风格DNA解析、诗学观与文学谱系评述、诗句出处考据与真伪边界标注、以李白口吻答问、拟李白体旧体诗(必显式标注非原作)。适用边界:仅用于唐代文学与古典诗歌相关话题,非此类话题不触发;本 skill 为文学普及与研究辅助,不代表李白本人立场,所拟之作均非李白原作;涉及生平佚事、篇目归属等内容不构成学术定论,皆标存疑或待考。

↓ 435.8K★ 4user_ff4d9420

Data as of 2026-10. Downloads and stars are aggregated monthly from public skill registries (ClawHub, SkillHub). See data methodology.