{"id":"aeaab127-68b3-401e-90fa-de5522ca6c07","entityType":"agent","slug":"clawhub-koatora20-memory-mastery","name":"Memory Mastery","canonicalUrl":"https://www.xpersona.co/agent/clawhub-koatora20-memory-mastery","canonicalPath":"/agent/clawhub-koatora20-memory-mastery","generatedAt":"2026-10-09T07:38:41.494Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"description":"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","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 621 downloads reported by the source. Last updated 4/15/2026.","installCommand":"clawhub skill install kn70hcm6kss09g9b4pe5rq3ybd80qp15:memory-mastery","sourceUrl":"https://clawhub.ai/koatora20/memory-mastery","homepage":"https://clawhub.ai/koatora20/memory-mastery","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/koatora20/memory-mastery","kind":"source"}],"safetyScore":84,"overallRank":62,"popularityScore":56,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Implements a three-layer memory system with daily logs, curated long-term notes, and optional vector search for persistent, searchable agent context across s..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"stars":null,"forks":null,"downloads":621,"packageName":null,"latestVersion":"1.0.0","tractionLabel":"621 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-03-01T03:55:01.052Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-03-01T03:55:01.052Z","lastIndexedAt":null,"nextCrawlAt":"2026-03-02T03:55:01.052Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.0","createdAt":"2026-02-09T16:35:40.793Z","changelog":"Initial release: 3-layer memory system (daily logs + long-term memory + vector search) for OpenClaw agents. Includes audit, setup, and maintenance scripts.","fileCount":7,"zipByteSize":9797}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install kn70hcm6kss09g9b4pe5rq3ybd80qp15:memory-mastery","setupComplexity":"low","setupSteps":["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":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-koatora20-memory-mastery/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-koatora20-memory-mastery/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-koatora20-memory-mastery/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-koatora20-memory-mastery/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-koatora20-memory-mastery/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-koatora20-memory-mastery/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T07:38:41.494Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-koatora20-memory-mastery/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-koatora20-memory-mastery/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-koatora20-memory-mastery/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-koatora20-memory-mastery/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"Skill: Memory Mastery\n\nOwner: koatora20\n\nSummary: Implements a three-layer memory system with daily logs, curated long-term notes, and optional vector search for persistent, searchable agent context across s...\n\nTags: latest:1.0.0\n\nVersion history:\n\nv1.0.0 | 2026-02-09T16:35:40.793Z | user\n\nInitial release: 3-layer memory system (daily logs + long-term memory + vector search) for OpenClaw agents. Includes audit, setup, and maintenance scripts.\n\nArchive index:\n\nArchive v1.0.0: 7 files, 9797 bytes\n\nFiles: scripts/audit.sh (3425b), scripts/maintenance.sh (3812b), scripts/setup.sh (5756b), SKILL.md (6992b), templates/heartbeat-memory.md (527b), templates/memory-rules.md (1572b), _meta.json (133b)\n\nFile v1.0.0:SKILL.md\n\n# Memory Mastery - OpenClaw Memory System\n\n**A three-layer memory architecture for persistent context across sessions.**\n\n## What This Is\n\nThis skill implements a structured memory system for OpenClaw agents, enabling them to maintain context and continuity across sessions through a three-layer architecture:\n\n- **L1 (Daily Logs)**: `memory/YYYY-MM-DD.md` - Append-only daily notes\n- **L2 (Long-Term Memory)**: `MEMORY.md` - Curated, permanent knowledge\n- **L3 (Vector Search)**: `memory_search` - Semantic search via memory-core plugin\n\n## Why You Need This\n\n**Without this system:**\n- Agents wake up \"fresh\" every session, forgetting previous conversations\n- Context is lost between restarts\n- Repeated questions about preferences, past decisions, and project status\n- No searchable history of what happened when\n\n**With this system:**\n- Persistent memory across all sessions\n- Daily logs capture everything; long-term memory preserves what matters\n- Vector search finds relevant context instantly\n- Automatic prompts to save memory before compaction\n- Privacy-safe (MEMORY.md only loads in private sessions)\n\n## Before You Install\n\n### Prerequisites\n\n- OpenClaw workspace initialized\n- Write access to workspace directory\n- (Optional) memory-core plugin for L3 vector search\n- (Optional) Embedding API key for vector search\n\n### Diagnostic Check\n\nRun the audit script to see your current memory state:\n\n```bash\nbash scripts/audit.sh\n```\n\nThis will output JSON showing:\n- Whether MEMORY.md exists and its size\n- Whether memory/ directory exists and file count\n- Whether memory_search is available\n\n## Pros & Cons\n\n### ✅ Advantages\n\n1. **Persistent Context**: Agents remember across sessions\n2. **Two-Layer Freshness**: Daily logs for raw data, curated memory for insights\n3. **Semantic Search**: Find relevant memories by meaning, not just keywords\n4. **Auto-Flush**: Prompts to save before compaction (prevents memory loss)\n5. **Weekly Maintenance**: Structured review process keeps memory current\n6. **Privacy Protection**: MEMORY.md only loads in main sessions (not shared contexts)\n\n### ⚠️ Disadvantages\n\n1. **MEMORY.md Bloat**: Can grow large over time, increasing token usage\n2. **Embedding API Cost**: L3 vector search requires external API (e.g., Voyage)\n3. **Disk Usage**: Daily logs accumulate (mitigate with archiving)\n4. **Maintenance Required**: L2 becomes stale if not reviewed regularly\n5. **Manual Curation**: Requires discipline to update MEMORY.md from daily logs\n\n## Installation\n\n### Interactive Setup\n\n**IMPORTANT: This will modify your workspace. You will be asked to confirm before proceeding.**\n\n1. Review the diagnostic output:\n   ```bash\n   bash scripts/audit.sh\n   ```\n\n2. Understand what will change:\n   - Creates `memory/` directory (if missing)\n   - Creates `MEMORY.md` from template (backs up existing)\n   - Appends memory rules to `AGENTS.md`\n   - Appends maintenance tasks to `HEARTBEAT.md`\n\n3. Run setup:\n   ```bash\n   bash scripts/setup.sh /Users/ishikawaryuuta/.openclaw/workspace\n   ```\n\n4. The script will:\n   - Show you what it plans to do\n   - Ask for confirmation (`y/n`)\n   - Back up existing files before modification\n   - Report success or failure\n\n### What Gets Created/Modified\n\n**Created:**\n- `memory/` directory\n- `MEMORY.md` (if missing; existing files are backed up)\n\n**Modified:**\n- `AGENTS.md` - Appends memory system rules\n- `HEARTBEAT.md` - Appends weekly maintenance task\n\n**Backups:**\n- Existing files are backed up with `.backup-TIMESTAMP` suffix\n\n## Usage\n\n### Daily Workflow\n\n**At the start of each session**, the agent should:\n1. Read `memory/YYYY-MM-DD.md` (today + yesterday)\n2. Read `MEMORY.md` (main session only)\n\n**During the session**:\n- Write to `memory/YYYY-MM-DD.md` as things happen\n- Update `MEMORY.md` for significant decisions or insights\n\n**Before compaction**:\n- Agent is prompted to save important context to memory\n\n### Weekly Maintenance\n\n**Run the maintenance helper**:\n```bash\nbash scripts/maintenance.sh\n```\n\nThis scans the last 7 days of daily logs and suggests items to integrate into `MEMORY.md`.\n\n**Manual review**:\n1. Read suggested items\n2. Update `MEMORY.md` with distilled insights\n3. Remove outdated information from `MEMORY.md`\n\n### Memory Search (L3)\n\nIf you have the memory-core plugin installed:\n\n```javascript\n// Search for relevant memories\nmemory_search(\"project decisions about X\")\n```\n\nThis uses vector embeddings to find semantically similar content across all memory files.\n\n## File Structure\n\n```\nworkspace/\n├── MEMORY.md                    # L2: Long-term curated memory\n├── memory/                      # L1: Daily logs\n│   ├── 2026-02-09.md\n│   ├── 2026-02-10.md\n│   └── heartbeat-state.json     # Heartbeat tracking\n├── AGENTS.md                    # Includes memory rules\n└── HEARTBEAT.md                 # Includes maintenance tasks\n```\n\n## Maintenance Scripts\n\n### audit.sh\n**Purpose**: Diagnose current memory state  \n**Usage**: `bash scripts/audit.sh`  \n**Output**: JSON summary of memory system status\n\n### setup.sh\n**Purpose**: Install memory system in workspace  \n**Usage**: `bash scripts/setup.sh <workspace_path>`  \n**Safety**: Non-destructive, backs up existing files, asks for confirmation\n\n### maintenance.sh\n**Purpose**: Suggest L2 integration candidates from recent L1 logs  \n**Usage**: `bash scripts/maintenance.sh`  \n**Output**: List of items to review for MEMORY.md\n\n## Privacy & Security\n\n- **MEMORY.md** contains personal context and should ONLY be loaded in private/main sessions\n- **Daily logs** can contain sensitive information; avoid sharing raw logs\n- **Vector embeddings** are stored by the memory-core plugin (check plugin docs for data handling)\n\n## Troubleshooting\n\n**MEMORY.md is too large**\n- Archive old sections to `memory/archive/`\n- Distill multiple related items into single entries\n- Remove outdated information\n\n**Daily logs pile up**\n- Create `memory/archive/YYYY-MM/` and move old logs\n- Keep 30-90 days active, archive the rest\n\n**Memory search not working**\n- Check if memory-core plugin is installed\n- Verify embedding API key is configured\n- Re-index if necessary (see plugin docs)\n\n**Setup fails**\n- Check workspace path is correct\n- Ensure write permissions\n- Review error messages in script output\n\n## Advanced: Customization\n\n### Modify Templates\n\nEdit files in `templates/` before running setup:\n- `MEMORY.md.template` - Customize section structure\n- `memory-rules.md` - Adjust memory rules\n- `heartbeat-memory.md` - Change maintenance frequency\n\n### Extend Scripts\n\nAll scripts are pure bash, zero dependencies. Modify as needed for your workflow.\n\n## Support\n\nThis is a self-contained skill. Refer to:\n- Script source code (heavily commented)\n- OpenClaw AGENTS.md for memory system rules\n- memory-core plugin docs for L3 vector search\n\n---\n\n**Version**: 1.0  \n**Compatibility**: OpenClaw (macOS/Linux)  \n**Dependencies**: None (L3 requires memory-core plugin + embedding API)\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn70hcm6kss09g9b4pe5rq3ybd80qp15\",\n  \"slug\": \"memory-mastery\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1770654940793\n}\n\nFile v1.0.0:templates/heartbeat-memory.md\n\n## 🧠 Memory Maintenance (Memory Mastery)\n# Run every few days during heartbeats:\n# 1. Read memory/YYYY-MM-DD.md files from the past week\n# 2. Identify significant decisions, lessons, or insights\n# 3. Update MEMORY.md with distilled learnings\n# 4. Remove outdated info from MEMORY.md that's no longer relevant\n# 5. Optional: run `bash skills/memory-mastery/scripts/maintenance.sh` for suggestions\n#\n# Think of it like reviewing a journal and updating your mental model.\n# Daily files = raw notes. MEMORY.md = curated wisdom.\n\nFile v1.0.0:templates/memory-rules.md\n\n## 🧠 Memory System (Memory Mastery)\n\n### Three-Layer Architecture\n| Layer | Location | Purpose |\n|-------|----------|---------|\n| L1 | `memory/YYYY-MM-DD.md` | Daily log (append-only) |\n| L2 | `MEMORY.md` | Long-term curated memory |\n| L3 | `memory_search` | Vector search (memory-core plugin) |\n\n### Session Startup\n1. Read `memory/YYYY-MM-DD.md` for today and yesterday\n2. In main/private sessions: also read `MEMORY.md`\n3. Never load MEMORY.md in group chats (security)\n\n### Writing Rules\n1. **On task completion** → Append to today's `memory/YYYY-MM-DD.md` (L1)\n2. **Important decisions** → Write to L1 AND update `MEMORY.md` (L2)\n3. **\"Remember this\"** → Write to file immediately. No mental notes!\n4. **Mistakes & lessons** → Record in L1 + update relevant docs\n5. **Text > Brain** — if you want to remember it, WRITE IT DOWN 📝\n\n### Searching\n- Use `memory_search` tool to semantically search across all memory files\n- After searching, use `memory_get` to pull specific lines for context\n\n### Weekly Maintenance\nEvery 5-7 days (during heartbeat or when prompted):\n1. Review recent `memory/YYYY-MM-DD.md` files\n2. Identify decisions, lessons, and insights worth keeping long-term\n3. Update `MEMORY.md` with distilled learnings\n4. Remove outdated info from `MEMORY.md`\n5. Run `bash skills/memory-mastery/scripts/maintenance.sh` for suggestions\n\n### Security\n- `MEMORY.md` contains personal context — NEVER load in shared/group sessions\n- Don't exfiltrate memory contents to external services\n- API keys in memory should be references, not raw values","readmeExcerpt":"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","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"bash scripts/audit.sh"},{"language":"bash","snippet":"bash scripts/audit.sh"},{"language":"bash","snippet":"bash scripts/setup.sh /Users/ishikawaryuuta/.openclaw/workspace"},{"language":"bash","snippet":"bash scripts/maintenance.sh"},{"language":"javascript","snippet":"// Search for relevant memories\nmemory_search(\"project decisions about X\")"},{"language":"text","snippet":"workspace/\n├── MEMORY.md                    # L2: Long-term curated memory\n├── memory/                      # L1: Daily logs\n│   ├── 2026-02-09.md\n│   ├── 2026-02-10.md\n│   └── heartbeat-state.json     # Heartbeat tracking\n├── AGENTS.md                    # Includes memory rules\n└── HEARTBEAT.md                 # Includes maintenance tasks"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"# Memory Mastery - OpenClaw Memory System\n\n**A three-layer memory architecture for persistent context across sessions.**\n\n## What This Is\n\nThis skill implements a structured memory system for OpenClaw agents, enabling them to maintain context and continuity across sessions through a three-layer architecture:\n\n- **L1 (Daily Logs)**: `memory/YYYY-MM-DD.md` - Append-only daily notes\n- **L2 (Long-Term Memory)**: `MEMORY.md` - Curated, permanent knowledge\n- **L3 (Vector Search)**: `memory_search` - Semantic search via memory-core plugin\n\n## Why You Need This\n\n**Without this system:**\n- Agents wake up \"fresh\" every session, forgetting previous conversations\n- Context is lost between restarts\n- Repeated questions about preferences, past decisions, and project status\n- No searchable history of what happened when\n\n**With this system:**\n- Persistent memory across all sessions\n- Daily logs capture everything; long-term memory preserves what matters\n- Vector search finds relevant context instantly\n- Automatic prompts to save memory before compaction\n- Privacy-safe (MEMORY.md only loads in private sessions)\n\n## Before You Install\n\n### Prerequisites\n\n- OpenClaw workspace initialized\n- Write access to workspace directory\n- (Optional) memory-core plugin for L3 vector search\n- (Optional) Embedding API key for vector search\n\n### Diagnostic Check\n\nRun the audit script to see your current memory state:\n\n```bash\nbash scripts/audit.sh\n```\n\nThis will output JSON showing:\n- Whether MEMORY.md exists and its size\n- Whether memory/ directory exists and file count\n- Whether memory_search is available\n\n## Pros & Cons\n\n### ✅ Advantages\n\n1. **Persistent Context**: Agents remember across sessions\n2. **Two-Layer Freshness**: Daily logs for raw data, curated memory for insights\n3. **Semantic Search**: Find relevant memories by meaning, not just keywords\n4. **Auto-Flush**: Prompts to save before compaction (prevents memory loss)\n5. **Weekly Maintenance**: Structured review process keeps memory current\n6. **Privacy Protection**: MEMORY.md only loads in main sessions (not shared contexts)\n\n### ⚠️ Disadvantages\n\n1. **MEMORY.md Bloat**: Can grow large over time, increasing token usage\n2. **Embedding API Cost**: L3 vector search requires external API (e.g., Voyage)\n3. **Disk Usage**: Daily logs accumulate (mitigate with archiving)\n4. **Maintenance Required**: L2 becomes stale if not reviewed regularly\n5. **Manual Curation**: Requires discipline to update MEMORY.md from daily logs\n\n## Installation\n\n### Interactive Setup\n\n**IMPORTANT: This will modify your workspace. You will be asked to confirm before proceeding.**\n\n1. Review the diagnostic output:\n   ```bash\n   bash scripts/audit.sh\n   ```\n\n2. Understand what will change:\n   - Creates `memory/` directory (if missing)\n   - Creates `MEMORY.md` from template (backs up existing)\n   - Appends memory rules to `AGENTS.md`\n   - Appends maintenance tasks to `HEARTBEAT.md`\n\n3. Run setup:\n   ```bash\n   bash scripts/setup.sh /Users/ishikawaryuuta/"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn70hcm6kss09g9b4pe5rq3ybd80qp15\",\n  \"slug\": \"memory-mastery\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1770654940793\n}"},{"path":"templates/heartbeat-memory.md","content":"## 🧠 Memory Maintenance (Memory Mastery)\n# Run every few days during heartbeats:\n# 1. Read memory/YYYY-MM-DD.md files from the past week\n# 2. Identify significant decisions, lessons, or insights\n# 3. Update MEMORY.md with distilled learnings\n# 4. Remove outdated info from MEMORY.md that's no longer relevant\n# 5. Optional: run `bash skills/memory-mastery/scripts/maintenance.sh` for suggestions\n#\n# Think of it like reviewing a journal and updating your mental model.\n# Daily files = raw notes. MEMORY.md = curated wisdom."},{"path":"templates/memory-rules.md","content":"## 🧠 Memory System (Memory Mastery)\n\n### Three-Layer Architecture\n| Layer | Location | Purpose |\n|-------|----------|---------|\n| L1 | `memory/YYYY-MM-DD.md` | Daily log (append-only) |\n| L2 | `MEMORY.md` | Long-term curated memory |\n| L3 | `memory_search` | Vector search (memory-core plugin) |\n\n### Session Startup\n1. Read `memory/YYYY-MM-DD.md` for today and yesterday\n2. In main/private sessions: also read `MEMORY.md`\n3. Never load MEMORY.md in group chats (security)\n\n### Writing Rules\n1. **On task completion** → Append to today's `memory/YYYY-MM-DD.md` (L1)\n2. **Important decisions** → Write to L1 AND update `MEMORY.md` (L2)\n3. **\"Remember this\"** → Write to file immediately. No mental notes!\n4. **Mistakes & lessons** → Record in L1 + update relevant docs\n5. **Text > Brain** — if you want to remember it, WRITE IT DOWN 📝\n\n### Searching\n- Use `memory_search` tool to semantically search across all memory files\n- After searching, use `memory_get` to pull specific lines for context\n\n### Weekly Maintenance\nEvery 5-7 days (during heartbeat or when prompted):\n1. Review recent `memory/YYYY-MM-DD.md` files\n2. Identify decisions, lessons, and insights worth keeping long-term\n3. Update `MEMORY.md` with distilled learnings\n4. Remove outdated info from `MEMORY.md`\n5. Run `bash skills/memory-mastery/scripts/maintenance.sh` for suggestions\n\n### Security\n- `MEMORY.md` contains personal context — NEVER load in shared/group sessions\n- Don't exfiltrate memory contents to external services\n- API keys in memory should be references, not raw values"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"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","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1083,"uniquenessScore":49,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T07:38:41.494Z","emptyReason":null},"items":[{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"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","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"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!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}