What makes Memory Mastery notable?

621 downloads. Trust evidence available

How should Memory Mastery 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 Mastery

Implements a three-layer memory system with daily logs, curated long-term notes, and optional vector search for persistent, searchable agent context across s... Skill: Memory Mastery Owner: koatora20 Summary: Implements a three-layer memory system with daily logs, curated long-term notes, and optional vector search for persistent, searchable agent context across s... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-02-09T16:35:40.793Z | user Initial release: 3-layer memory system (daily logs + long-term memory + vector search) for OpenClaw agents. Includes audit, setup, and

OpenClaw

View on ClawHub

Rank

Safety

Downloads

621

Updated

Apr 15, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 621 downloads reported by the source. Last updated 4/15/2026.

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 Apr 15, 2026
Protocol compatibility: OpenClawcompatibility · observed Apr 15, 2026
Adoption signal: 621 downloadsadoption · observed Apr 15, 2026
Latest release: 1.0.0release · observed Feb 9, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install kn70hcm6kss09g9b4pe5rq3ybd80qp15:memory-mastery

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-koatora20-memory-mastery/snapshot"

Documentation

CLAWHUB

9,986 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

# Memory Mastery - OpenClaw Memory System

**A three-layer memory architecture for persistent context across sessions.**

## What This Is

This skill implements a structured memory system for OpenClaw agents, enabling them to maintain context and continuity across sessions through a three-layer architecture:

- **L1 (Daily Logs)**: `memory/YYYY-MM-DD.md` - Append-only daily notes
- **L2 (Long-Term Memory)**: `MEMORY.md` - Curated, permanent knowledge
- **L3 (Vector Search)**: `memory_search` - Semantic search via memory-core plugin

## Why You Need This

**Without this system:**
- Agents wake up "fresh" every session, forgetting previous conversations
- Context is lost between restarts
- Repeated questions about preferences, past decisions, and project status
- No searchable history of what happened when

**With this system:**
- Persistent memory across all sessions
- Daily logs capture everything; long-term memory preserves what matters
- Vector search finds relevant context instantly
- Automatic prompts to save memory before compaction
- Privacy-safe (MEMORY.md only loads in private sessions)

## Before You Install

### Prerequisites

- OpenClaw workspace initialized
- Write access to workspace directory
- (Optional) memory-core plugin for L3 vector search
- (Optional) Embedding API key for vector search

### Diagnostic Check

Run the audit script to see your current memory state:

```bash
bash scripts/audit.sh
```

This will output JSON showing:
- Whether MEMORY.md exists and its size
- Whether memory/ directory exists and file count
- Whether memory_search is available

## Pros & Cons

### ✅ Advantages

1. **Persistent Context**: Agents remember across sessions
2. **Two-Layer Freshness**: Daily logs for raw data, curated memory for insights
3. **Semantic Search**: Find relevant memories by meaning, not just keywords
4. **Auto-Flush**: Prompts to save before compaction (prevents memory loss)
5. **Weekly Maintenance**: Structured review process keeps memory current
6. **Privacy Protection**: MEMORY.md only loads in main sessions (not shared contexts)

### ⚠️ Disadvantages

1. **MEMORY.md Bloat**: Can grow large over time, increasing token usage
2. **Embedding API Cost**: L3 vector search requires external API (e.g., Voyage)
3. **Disk Usage**: Daily logs accumulate (mitigate with archiving)
4. **Maintenance Required**: L2 becomes stale if not reviewed regularly
5. **Manual Curation**: Requires discipline to update MEMORY.md from daily logs

## Installation

### Interactive Setup

**IMPORTANT: This will modify your workspace. You will be asked to confirm before proceeding.**

1. Review the diagnostic output:
   ```bash
   bash scripts/audit.sh
   ```

2. Understand what will change:
   - Creates `memory/` directory (if missing)
   - Creates `MEMORY.md` from template (backs up existing)
   - Appends memory rules to `AGENTS.md`
   - Appends maintenance tasks to `HEARTBEAT.md`

3. Run setup:
   ```bash
   bash scripts/setup.sh /Users/ishikawaryuuta/

_meta.json

{
  "ownerId": "kn70hcm6kss09g9b4pe5rq3ybd80qp15",
  "slug": "memory-mastery",
  "version": "1.0.0",
  "publishedAt": 1770654940793
}

templates/heartbeat-memory.md

## 🧠 Memory Maintenance (Memory Mastery)
# Run every few days during heartbeats:
# 1. Read memory/YYYY-MM-DD.md files from the past week
# 2. Identify significant decisions, lessons, or insights
# 3. Update MEMORY.md with distilled learnings
# 4. Remove outdated info from MEMORY.md that's no longer relevant
# 5. Optional: run `bash skills/memory-mastery/scripts/maintenance.sh` for suggestions
#
# Think of it like reviewing a journal and updating your mental model.
# Daily files = raw notes. MEMORY.md = curated wisdom.

templates/memory-rules.md

## 🧠 Memory System (Memory Mastery)

### Three-Layer Architecture
| Layer | Location | Purpose |
|-------|----------|---------|
| L1 | `memory/YYYY-MM-DD.md` | Daily log (append-only) |
| L2 | `MEMORY.md` | Long-term curated memory |
| L3 | `memory_search` | Vector search (memory-core plugin) |

### Session Startup
1. Read `memory/YYYY-MM-DD.md` for today and yesterday
2. In main/private sessions: also read `MEMORY.md`
3. Never load MEMORY.md in group chats (security)

### Writing Rules
1. **On task completion** → Append to today's `memory/YYYY-MM-DD.md` (L1)
2. **Important decisions** → Write to L1 AND update `MEMORY.md` (L2)
3. **"Remember this"** → Write to file immediately. No mental notes!
4. **Mistakes & lessons** → Record in L1 + update relevant docs
5. **Text > Brain** — if you want to remember it, WRITE IT DOWN 📝

### Searching
- Use `memory_search` tool to semantically search across all memory files
- After searching, use `memory_get` to pull specific lines for context

### Weekly Maintenance
Every 5-7 days (during heartbeat or when prompted):
1. Review recent `memory/YYYY-MM-DD.md` files
2. Identify decisions, lessons, and insights worth keeping long-term
3. Update `MEMORY.md` with distilled learnings
4. Remove outdated info from `MEMORY.md`
5. Run `bash skills/memory-mastery/scripts/maintenance.sh` for suggestions

### Security
- `MEMORY.md` contains personal context — NEVER load in shared/group sessions
- Don't exfiltrate memory contents to external services
- API keys in memory should be references, not raw values

Github ReposUpdated 5h 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.