Skill: Elite Longterm Memory

Owner: nextfrontierbuilds

Summary: Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.

Tags: latest:1.2.3, ai:0.1.0, clawdbot:0.1.0, long-term:0.1.0, memory:0.1.0, openclaw:0.1.0, persistence:0.1.0

Version history:

v1.2.3 | 2026-02-11T08:37:00.241Z | auto

• Expanded description and keywords for improved discoverability, highlighting ChatGPT, Copilot, Cursor, and developer tooling.
• Updated version to 1.2.3.
• Clarified compatibility and marketing text in SKILL.md.
• No functional or implementation changes to code logic.

v1.2.2 | 2026-02-04T15:59:05.664Z | user

Rebranded to OpenClaw

v1.2.1 | 2026-02-04T15:44:05.285Z | user

SEO update: added claude-code, cursor, copilot, agentic keywords

v0.1.0 | 2026-02-02T16:37:23.398Z | auto

Major upgrade: Combines 6 advanced memory systems for AI agents into a single robust architecture.

• Integrates Write-Ahead Log session memory, LanceDB vector search, git-notes knowledge graphs, curated long-term logs, cloud backup, and optional auto-extraction.
• Adds new auto-extraction tier (Mem0) for fact preference/decision extraction, enabling 80% token reduction.
• Provides clear agent usage protocols to maintain durability and prevent context loss.
• Extensive setup and workflow guides for seamless deployment with Clawdbot, Moltbot, Claude, and GPT agents.

Archive index:

Archive v1.2.3: 6 files, 10862 bytes

Files: bin/elite-memory.js (4875b), package.json (1288b), README.md (5593b), skill-card.md (2575b), SKILL.md (12723b), _meta.json (140b)

File v1.2.3:SKILL.md

---

name: elite-longterm-memory version: 1.2.3 description: "Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready." author: NextFrontierBuilds keywords: [memory, ai-agent, ai-coding, long-term-memory, vector-search, lancedb, git-notes, wal, persistent-context, claude, claude-code, gpt, chatgpt, cursor, copilot, github-copilot, openclaw, moltbot, vibe-coding, agentic, ai-tools, developer-tools, devtools, typescript, llm, automation] metadata: openclaw: emoji: "🧠" requires: env: - OPENAI_API_KEY plugins: - memory-lancedb

Elite Longterm Memory 🧠

The ultimate memory system for AI agents. Combines 6 proven approaches into one bulletproof architecture.

Never lose context. Never forget decisions. Never repeat mistakes.

Architecture Overview

┌─────────────────────────────────────────────────────────────────┐
│                    ELITE LONGTERM MEMORY                        │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐             │
│  │   HOT RAM   │  │  WARM STORE │  │  COLD STORE │             │
│  │             │  │             │  │             │             │
│  │ SESSION-    │  │  LanceDB    │  │  Git-Notes  │             │
│  │ STATE.md    │  │  Vectors    │  │  Knowledge  │             │
│  │             │  │             │  │  Graph      │             │
│  │ (survives   │  │ (semantic   │  │ (permanent  │             │
│  │  compaction)│  │  search)    │  │  decisions) │             │
│  └─────────────┘  └─────────────┘  └─────────────┘             │
│         │                │                │                     │
│         └────────────────┼────────────────┘                     │
│                          ▼                                      │
│                  ┌─────────────┐                                │
│                  │  MEMORY.md  │  ← Curated long-term           │
│                  │  + daily/   │    (human-readable)            │
│                  └─────────────┘                                │
│                          │                                      │
│                          ▼                                      │
│                  ┌─────────────┐                                │
│                  │ SuperMemory │  ← Cloud backup (optional)     │
│                  │    API      │                                │
│                  └─────────────┘                                │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

The 5 Memory Layers

Layer 1: HOT RAM (SESSION-STATE.md)

From: bulletproof-memory

Active working memory that survives compaction. Write-Ahead Log protocol.

# SESSION-STATE.md — Active Working Memory

## Current Task
[What we're working on RIGHT NOW]

## Key Context
- User preference: ...
- Decision made: ...
- Blocker: ...

## Pending Actions
- [ ] ...

Rule: Write BEFORE responding. Triggered by user input, not agent memory.

Layer 2: WARM STORE (LanceDB Vectors)

From: lancedb-memory

Semantic search across all memories. Auto-recall injects relevant context.

# Auto-recall (happens automatically)
memory_recall query="project status" limit=5

# Manual store
memory_store text="User prefers dark mode" category="preference" importance=0.9

Layer 3: COLD STORE (Git-Notes Knowledge Graph)

From: git-notes-memory

Structured decisions, learnings, and context. Branch-aware.

# Store a decision (SILENT - never announce)
python3 memory.py -p $DIR remember '{"type":"decision","content":"Use React for frontend"}' -t tech -i h

# Retrieve context
python3 memory.py -p $DIR get "frontend"

Layer 4: CURATED ARCHIVE (MEMORY.md + daily/)

From: OpenClaw native

Human-readable long-term memory. Daily logs + distilled wisdom.

workspace/
├── MEMORY.md              # Curated long-term (the good stuff)
└── memory/
    ├── 2026-01-30.md      # Daily log
    ├── 2026-01-29.md
    └── topics/            # Topic-specific files

Layer 5: CLOUD BACKUP (SuperMemory) — Optional

From: supermemory

Cross-device sync. Chat with your knowledge base.

export SUPERMEMORY_API_KEY="your-key"
supermemory add "Important context"
supermemory search "what did we decide about..."

Layer 6: AUTO-EXTRACTION (Mem0) — Recommended

NEW: Automatic fact extraction

Mem0 automatically extracts facts from conversations. 80% token reduction.

npm install mem0ai
export MEM0_API_KEY="your-key"

const { MemoryClient } = require('mem0ai');
const client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });

// Conversations auto-extract facts
await client.add(messages, { user_id: "user123" });

// Retrieve relevant memories
const memories = await client.search(query, { user_id: "user123" });

Benefits:

• Auto-extracts preferences, decisions, facts
• Deduplicates and updates existing memories
• 80% reduction in tokens vs raw history
• Works across sessions automatically

Quick Setup

1. Create SESSION-STATE.md (Hot RAM)

cat > SESSION-STATE.md << 'EOF'
# SESSION-STATE.md — Active Working Memory

This file is the agent's "RAM" — survives compaction, restarts, distractions.

## Current Task
[None]

## Key Context
[None yet]

## Pending Actions
- [ ] None

## Recent Decisions
[None yet]

---
*Last updated: [timestamp]*
EOF

2. Enable LanceDB (Warm Store)

In ~/.openclaw/openclaw.json:

{
  "memorySearch": {
    "enabled": true,
    "provider": "openai",
    "sources": ["memory"],
    "minScore": 0.3,
    "maxResults": 10
  },
  "plugins": {
    "entries": {
      "memory-lancedb": {
        "enabled": true,
        "config": {
          "autoCapture": false,
          "autoRecall": true,
          "captureCategories": ["preference", "decision", "fact"],
          "minImportance": 0.7
        }
      }
    }
  }
}

3. Initialize Git-Notes (Cold Store)

cd ~/clawd
git init  # if not already
python3 skills/git-notes-memory/memory.py -p . sync --start

4. Verify MEMORY.md Structure

# Ensure you have:
# - MEMORY.md in workspace root
# - memory/ folder for daily logs
mkdir -p memory

5. (Optional) Setup SuperMemory

export SUPERMEMORY_API_KEY="your-key"
# Add to ~/.zshrc for persistence

Agent Instructions

On Session Start

1. Read SESSION-STATE.md — this is your hot context
2. Run memory_search for relevant prior context
3. Check memory/YYYY-MM-DD.md for recent activity

During Conversation

1. User gives concrete detail? → Write to SESSION-STATE.md BEFORE responding
2. Important decision made? → Store in Git-Notes (SILENTLY)
3. Preference expressed? → memory_store with importance=0.9

On Session End

1. Update SESSION-STATE.md with final state
2. Move significant items to MEMORY.md if worth keeping long-term
3. Create/update daily log in memory/YYYY-MM-DD.md

Memory Hygiene (Weekly)

1. Review SESSION-STATE.md — archive completed tasks
2. Check LanceDB for junk: memory_recall query="*" limit=50
3. Clear irrelevant vectors: memory_forget id=<id>
4. Consolidate daily logs into MEMORY.md

The WAL Protocol (Critical)

Write-Ahead Log: Write state BEFORE responding, not after.

| Trigger | Action | |---------|--------| | User states preference | Write to SESSION-STATE.md → then respond | | User makes decision | Write to SESSION-STATE.md → then respond | | User gives deadline | Write to SESSION-STATE.md → then respond | | User corrects you | Write to SESSION-STATE.md → then respond |

Why? If you respond first and crash/compact before saving, context is lost. WAL ensures durability.

Example Workflow

User: "Let's use Tailwind for this project, not vanilla CSS"

Agent (internal):
1. Write to SESSION-STATE.md: "Decision: Use Tailwind, not vanilla CSS"
2. Store in Git-Notes: decision about CSS framework
3. memory_store: "User prefers Tailwind over vanilla CSS" importance=0.9
4. THEN respond: "Got it — Tailwind it is..."

Maintenance Commands

# Audit vector memory
memory_recall query="*" limit=50

# Clear all vectors (nuclear option)
rm -rf ~/.openclaw/memory/lancedb/
openclaw gateway restart

# Export Git-Notes
python3 memory.py -p . export --format json > memories.json

# Check memory health
du -sh ~/.openclaw/memory/
wc -l MEMORY.md
ls -la memory/

Why Memory Fails

Understanding the root causes helps you fix them:

| Failure Mode | Cause | Fix | |--------------|-------|-----| | Forgets everything | memory_search disabled | Enable + add OpenAI key | | Files not loaded | Agent skips reading memory | Add to AGENTS.md rules | | Facts not captured | No auto-extraction | Use Mem0 or manual logging | | Sub-agents isolated | Don't inherit context | Pass context in task prompt | | Repeats mistakes | Lessons not logged | Write to memory/lessons.md |

Solutions (Ranked by Effort)

1. Quick Win: Enable memory_search

If you have an OpenAI key, enable semantic search:

openclaw configure --section web

This enables vector search over MEMORY.md + memory/*.md files.

2. Recommended: Mem0 Integration

Auto-extract facts from conversations. 80% token reduction.

npm install mem0ai

const { MemoryClient } = require('mem0ai');

const client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });

// Auto-extract and store
await client.add([
  { role: "user", content: "I prefer Tailwind over vanilla CSS" }
], { user_id: "ty" });

// Retrieve relevant memories
const memories = await client.search("CSS preferences", { user_id: "ty" });

3. Better File Structure (No Dependencies)

memory/
├── projects/
│   ├── strykr.md
│   └── taska.md
├── people/
│   └── contacts.md
├── decisions/
│   └── 2026-01.md
├── lessons/
│   └── mistakes.md
└── preferences.md

Keep MEMORY.md as a summary (<5KB), link to detailed files.

Immediate Fixes Checklist

| Problem | Fix | |---------|-----| | Forgets preferences | Add ## Preferences section to MEMORY.md | | Repeats mistakes | Log every mistake to memory/lessons.md | | Sub-agents lack context | Include key context in spawn task prompt | | Forgets recent work | Strict daily file discipline | | Memory search not working | Check OPENAI_API_KEY is set |

Troubleshooting

Agent keeps forgetting mid-conversation: → SESSION-STATE.md not being updated. Check WAL protocol.

Irrelevant memories injected: → Disable autoCapture, increase minImportance threshold.

Memory too large, slow recall: → Run hygiene: clear old vectors, archive daily logs.

Git-Notes not persisting: → Run git notes push to sync with remote.

memory_search returns nothing: → Check OpenAI API key: echo $OPENAI_API_KEY → Verify memorySearch enabled in openclaw.json

---

Links

• bulletproof-memory: https://clawdhub.com/skills/bulletproof-memory
• lancedb-memory: https://clawdhub.com/skills/lancedb-memory
• git-notes-memory: https://clawdhub.com/skills/git-notes-memory
• memory-hygiene: https://clawdhub.com/skills/memory-hygiene
• supermemory: https://clawdhub.com/skills/supermemory

---

Built by @NextXFrontier — Part of the Next Frontier AI toolkit

File v1.2.3:README.md

Elite Longterm Memory 🧠

The ultimate memory system for AI agents. Never lose context again.

---

Works With

<p align="center"> <img src="https://img.shields.io/badge/Claude-AI-orange?style=for-the-badge&logo=anthropic" alt="Claude AI" /> <img src="https://img.shields.io/badge/GPT-OpenAI-412991?style=for-the-badge&logo=openai" alt="GPT" /> <img src="https://img.shields.io/badge/Cursor-IDE-000000?style=for-the-badge" alt="Cursor" /> <img src="https://img.shields.io/badge/LangChain-Framework-1C3C3C?style=for-the-badge" alt="LangChain" /> </p> <p align="center"> <strong>Built for:</strong> Clawdbot • Moltbot • Claude Code • Any AI Agent </p>

---

Combines 7 proven memory approaches into one bulletproof architecture:

• ✅ Bulletproof WAL Protocol — Write-ahead logging survives compaction
• ✅ LanceDB Vector Search — Semantic recall of relevant memories
• ✅ Git-Notes Knowledge Graph — Structured decisions, branch-aware
• ✅ File-Based Archives — Human-readable MEMORY.md + daily logs
• ✅ Cloud Backup — Optional SuperMemory sync
• ✅ Memory Hygiene — Keep vectors lean, prevent token waste
• ✅ Mem0 Auto-Extraction — Automatic fact extraction, 80% token reduction

Quick Start

# Initialize in your workspace
npx elite-longterm-memory init

# Check status
npx elite-longterm-memory status

# Create today's log
npx elite-longterm-memory today

Architecture

┌─────────────────────────────────────────────────────┐
│              ELITE LONGTERM MEMORY                  │
├─────────────────────────────────────────────────────┤
│  HOT RAM          WARM STORE        COLD STORE     │
│  SESSION-STATE.md → LanceDB      → Git-Notes       │
│  (survives         (semantic       (permanent      │
│   compaction)       search)         decisions)     │
│         │              │                │          │
│         └──────────────┼────────────────┘          │
│                        ▼                           │
│                   MEMORY.md                        │
│               (curated archive)                    │
└─────────────────────────────────────────────────────┘

The 5 Memory Layers

| Layer | File/System | Purpose | Persistence | |-------|-------------|---------|-------------| | 1. Hot RAM | SESSION-STATE.md | Active task context | Survives compaction | | 2. Warm Store | LanceDB | Semantic search | Auto-recall | | 3. Cold Store | Git-Notes | Structured decisions | Permanent | | 4. Archive | MEMORY.md + daily/ | Human-readable | Curated | | 5. Cloud | SuperMemory | Cross-device sync | Optional |

The WAL Protocol

Critical insight: Write state BEFORE responding, not after.

User: "Let's use Tailwind for this project"

Agent (internal):
1. Write to SESSION-STATE.md → "Decision: Use Tailwind"
2. THEN respond → "Got it — Tailwind it is..."

If you respond first and crash before saving, context is lost. WAL ensures durability.

Why Memory Fails (And How to Fix It)

| Problem | Cause | Fix | |---------|-------|-----| | Forgets everything | memory_search disabled | Enable + add OpenAI key | | Repeats mistakes | Lessons not logged | Write to memory/lessons.md | | Sub-agents isolated | No context inheritance | Pass context in task prompt | | Facts not captured | No auto-extraction | Use Mem0 (see below) |

Mem0 Integration (Recommended)

Auto-extract facts from conversations. 80% token reduction.

npm install mem0ai
export MEM0_API_KEY="your-key"

const { MemoryClient } = require('mem0ai');
const client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });

// Auto-extracts facts from messages
await client.add(messages, { user_id: "user123" });

// Retrieve relevant memories  
const memories = await client.search(query, { user_id: "user123" });

For Clawdbot/Moltbot Users

Add to ~/.clawdbot/clawdbot.json:

{
  "memorySearch": {
    "enabled": true,
    "provider": "openai",
    "sources": ["memory"]
  }
}

Files Created

workspace/
├── SESSION-STATE.md    # Hot RAM (active context)
├── MEMORY.md           # Curated long-term memory
└── memory/
    ├── 2026-01-30.md   # Daily logs
    └── ...

Commands

elite-memory init      # Initialize memory system
elite-memory status    # Check health
elite-memory today     # Create today's log
elite-memory help      # Show help

Links

• Full Documentation (SKILL.md)
• ClawdHub
• GitHub

---

Built by @NextXFrontier

File v1.2.3:_meta.json

{ "ownerId": "kn7ewywaj7mf48drbjw1baa5298016yv", "slug": "elite-longterm-memory", "version": "1.2.3", "publishedAt": 1770799020241 }

File v1.2.3:skill-card.md

Description: <br>

Elite Longterm Memory helps AI agents preserve project context with write-ahead logs, vector search, git-notes, local memory files, and optional cloud backup. <br>

This skill is ready for commercial/non-commercial use. <br>

Publisher: <br>

NextFrontierBuilds <br>

License/Terms of Use: <br>

MIT <br>

Use Case: <br>

Developers and agent users use this skill to initialize and maintain project memory files, daily logs, and recall configuration so agents can preserve preferences, decisions, lessons, and task context across sessions. <br>

Deployment Geography for Use: <br>

Global <br>

Known Risks and Mitigations: <br>

Risk: The skill encourages agents to retain project and preference context, which can accidentally preserve sensitive, private, or regulated details. <br> Mitigation: Require approval before saving sensitive details, summarize instead of copying raw conversation text, and review or delete stored memory regularly. <br> Risk: Optional Mem0 or SuperMemory use may send memory content to external cloud services. <br> Mitigation: Enable cloud memory only with approved providers, trusted API keys, and clear permission for the type of data being stored. <br> Risk: Persisted memories can become stale or misleading and may influence later agent work. <br> Mitigation: Run routine memory hygiene, keep high-value summaries curated, and review recalled context before relying on it for decisions. <br>

Reference(s): <br>

• ClawHub Skill Page <br>
• Full Documentation <br>
• Skill Instructions <br>
• NPM Package <br>

Skill Output: <br>

Output Type(s): [text, markdown, shell commands, configuration, guidance] <br> Output Format: [Markdown guidance with shell commands, JSON configuration examples, and generated local Markdown memory files] <br> Output Parameters: [1D] <br> Other Properties Related to Output: [Creates and updates local SESSION-STATE.md, MEMORY.md, and memory/*.md files when the CLI is used.] <br>

Skill Version(s): <br>

1.2.3 (source: evidence release, SKILL.md frontmatter, and package.json) <br>

Ethical Considerations: <br>

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. <br>

File v1.2.3:package.json

{ "name": "elite-longterm-memory", "version": "1.2.3", "description": "Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol, vector search, git-based knowledge graphs, cloud backup. Never lose context again.", "keywords": [ "memory", "ai-agent", "long-term-memory", "vector-search", "lancedb", "git-notes", "wal", "persistent-context", "claude", "gpt", "chatgpt", "openclaw", "moltbot", "cursor", "copilot", "github-copilot", "ai", "llm", "automation", "context-management", "mem0", "auto-extraction", "fact-extraction", "vibe-coding", "ai-tools", "developer-tools", "devtools", "typescript" ], "optionalDependencies": { "mem0ai": "^1.0.0" }, "author": "NextFrontierBuilds", "license": "MIT", "repository": { "type": "git", "url": "https://github.com/NextFrontierBuilds/elite-longterm-memory" }, "homepage": "https://github.com/NextFrontierBuilds/elite-longterm-memory", "bugs": { "url": "https://github.com/NextFrontierBuilds/elite-longterm-memory/issues" }, "bin": { "elite-memory": "./bin/elite-memory.js" }, "files": [ "SKILL.md", "bin/", "templates/", "README.md" ] }

Archive v1.2.2: 5 files, 9444 bytes

Files: bin/elite-memory.js (4875b), package.json (1183b), README.md (5593b), SKILL.md (12634b), _meta.json (140b)

File v1.2.2:SKILL.md

---

name: elite-longterm-memory version: 1.2.1 description: "Ultimate AI agent memory system. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Works with Claude, Cursor, GPT, OpenClaw agents." author: NextFrontierBuilds keywords: [memory, ai-agent, ai-coding, long-term-memory, vector-search, lancedb, git-notes, wal, persistent-context, claude, claude-code, gpt, cursor, copilot, openclaw, moltbot, openclaw, vibe-coding, agentic] metadata: openclaw: emoji: "🧠" requires: env: - OPENAI_API_KEY plugins: - memory-lancedb

Elite Longterm Memory 🧠

The ultimate memory system for AI agents. Combines 6 proven approaches into one bulletproof architecture.

Never lose context. Never forget decisions. Never repeat mistakes.

Architecture Overview

┌─────────────────────────────────────────────────────────────────┐
│                    ELITE LONGTERM MEMORY                        │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐             │
│  │   HOT RAM   │  │  WARM STORE │  │  COLD STORE │             │
│  │             │  │             │  │             │             │
│  │ SESSION-    │  │  LanceDB    │  │  Git-Notes  │             │
│  │ STATE.md    │  │  Vectors    │  │  Knowledge  │             │
│  │             │  │             │  │  Graph      │             │
│  │ (survives   │  │ (semantic   │  │ (permanent  │             │
│  │  compaction)│  │  search)    │  │  decisions) │             │
│  └─────────────┘  └─────────────┘  └─────────────┘             │
│         │                │                │                     │
│         └────────────────┼────────────────┘                     │
│                          ▼                                      │
│                  ┌─────────────┐                                │
│                  │  MEMORY.md  │  ← Curated long-term           │
│                  │  + daily/   │    (human-readable)            │
│                  └─────────────┘                                │
│                          │                                      │
│                          ▼                                      │
│                  ┌─────────────┐                                │
│                  │ SuperMemory │  ← Cloud backup (optional)     │
│                  │    API      │                                │
│                  └─────────────┘                                │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

The 5 Memory Layers

Layer 1: HOT RAM (SESSION-STATE.md)

From: bulletproof-memory

Active working memory that survives compaction. Write-Ahead Log protocol.

# SESSION-STATE.md — Active Working Memory

## Current Task
[What we're working on RIGHT NOW]

## Key Context
- User preference: ...
- Decision made: ...
- Blocker: ...

## Pending Actions
- [ ] ...

Rule: Write BEFORE responding. Triggered by user input, not agent memory.

Layer 2: WARM STORE (LanceDB Vectors)

From: lancedb-memory

Semantic search across all memories. Auto-recall injects relevant context.

# Auto-recall (happens automatically)
memory_recall query="project status" limit=5

# Manual store
memory_store text="User prefers dark mode" category="preference" importance=0.9

Layer 3: COLD STORE (Git-Notes Knowledge Graph)

From: git-notes-memory

Structured decisions, learnings, and context. Branch-aware.

# Store a decision (SILENT - never announce)
python3 memory.py -p $DIR remember '{"type":"decision","content":"Use React for frontend"}' -t tech -i h

# Retrieve context
python3 memory.py -p $DIR get "frontend"

Layer 4: CURATED ARCHIVE (MEMORY.md + daily/)

From: OpenClaw native

Human-readable long-term memory. Daily logs + distilled wisdom.

workspace/
├── MEMORY.md              # Curated long-term (the good stuff)
└── memory/
    ├── 2026-01-30.md      # Daily log
    ├── 2026-01-29.md
    └── topics/            # Topic-specific files

Layer 5: CLOUD BACKUP (SuperMemory) — Optional

From: supermemory

Cross-device sync. Chat with your knowledge base.

export SUPERMEMORY_API_KEY="your-key"
supermemory add "Important context"
supermemory search "what did we decide about..."

Layer 6: AUTO-EXTRACTION (Mem0) — Recommended

NEW: Automatic fact extraction

Mem0 automatically extracts facts from conversations. 80% token reduction.

npm install mem0ai
export MEM0_API_KEY="your-key"

const { MemoryClient } = require('mem0ai');
const client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });

// Conversations auto-extract facts
await client.add(messages, { user_id: "user123" });

// Retrieve relevant memories
const memories = await client.search(query, { user_id: "user123" });

Benefits:

• Auto-extracts preferences, decisions, facts
• Deduplicates and updates existing memories
• 80% reduction in tokens vs raw history
• Works across sessions automatically

Quick Setup

1. Create SESSION-STATE.md (Hot RAM)

cat > SESSION-STATE.md << 'EOF'
# SESSION-STATE.md — Active Working Memory

This file is the agent's "RAM" — survives compaction, restarts, distractions.

## Current Task
[None]

## Key Context
[None yet]

## Pending Actions
- [ ] None

## Recent Decisions
[None yet]

---
*Last updated: [timestamp]*
EOF

2. Enable LanceDB (Warm Store)

In ~/.openclaw/openclaw.json:

{
  "memorySearch": {
    "enabled": true,
    "provider": "openai",
    "sources": ["memory"],
    "minScore": 0.3,
    "maxResults": 10
  },
  "plugins": {
    "entries": {
      "memory-lancedb": {
        "enabled": true,
        "config": {
          "autoCapture": false,
          "autoRecall": true,
          "captureCategories": ["preference", "decision", "fact"],
          "minImportance": 0.7
        }
      }
    }
  }
}

3. Initialize Git-Notes (Cold Store)

cd ~/clawd
git init  # if not already
python3 skills/git-notes-memory/memory.py -p . sync --start

4. Verify MEMORY.md Structure

# Ensure you have:
# - MEMORY.md in workspace root
# - memory/ folder for daily logs
mkdir -p memory

5. (Optional) Setup SuperMemory

export SUPERMEMORY_API_KEY="your-key"
# Add to ~/.zshrc for persistence

Agent Instructions

On Session Start

1. Read SESSION-STATE.md — this is your hot context
2. Run memory_search for relevant prior context
3. Check memory/YYYY-MM-DD.md for recent activity

During Conversation

1. User gives concrete detail? → Write to SESSION-STATE.md BEFORE responding
2. Important decision made? → Store in Git-Notes (SILENTLY)
3. Preference expressed? → memory_store with importance=0.9

On Session End

1. Update SESSION-STATE.md with final state
2. Move significant items to MEMORY.md if worth keeping long-term
3. Create/update daily log in memory/YYYY-MM-DD.md

Memory Hygiene (Weekly)

1. Review SESSION-STATE.md — archive completed tasks
2. Check LanceDB for junk: memory_recall query="*" limit=50
3. Clear irrelevant vectors: memory_forget id=<id>
4. Consolidate daily logs into MEMORY.md

The WAL Protocol (Critical)

Write-Ahead Log: Write state BEFORE responding, not after.

| Trigger | Action | |---------|--------| | User states preference | Write to SESSION-STATE.md → then respond | | User makes decision | Write to SESSION-STATE.md → then respond | | User gives deadline | Write to SESSION-STATE.md → then respond | | User corrects you | Write to SESSION-STATE.md → then respond |

Why? If you respond first and crash/compact before saving, context is lost. WAL ensures durability.

Example Workflow

User: "Let's use Tailwind for this project, not vanilla CSS"

Agent (internal):
1. Write to SESSION-STATE.md: "Decision: Use Tailwind, not vanilla CSS"
2. Store in Git-Notes: decision about CSS framework
3. memory_store: "User prefers Tailwind over vanilla CSS" importance=0.9
4. THEN respond: "Got it — Tailwind it is..."

Maintenance Commands

# Audit vector memory
memory_recall query="*" limit=50

# Clear all vectors (nuclear option)
rm -rf ~/.openclaw/memory/lancedb/
openclaw gateway restart

# Export Git-Notes
python3 memory.py -p . export --format json > memories.json

# Check memory health
du -sh ~/.openclaw/memory/
wc -l MEMORY.md
ls -la memory/

Why Memory Fails

Understanding the root causes helps you fix them:

| Failure Mode | Cause | Fix | |--------------|-------|-----| | Forgets everything | memory_search disabled | Enable + add OpenAI key | | Files not loaded | Agent skips reading memory | Add to AGENTS.md rules | | Facts not captured | No auto-extraction | Use Mem0 or manual logging | | Sub-agents isolated | Don't inherit context | Pass context in task prompt | | Repeats mistakes | Lessons not logged | Write to memory/lessons.md |

Solutions (Ranked by Effort)

1. Quick Win: Enable memory_search

If you have an OpenAI key, enable semantic search:

openclaw configure --section web

This enables vector search over MEMORY.md + memory/*.md files.

2. Recommended: Mem0 Integration

Auto-extract facts from conversations. 80% token reduction.

npm install mem0ai

const { MemoryClient } = require('mem0ai');

const client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });

// Auto-extract and store
await client.add([
  { role: "user", content: "I prefer Tailwind over vanilla CSS" }
], { user_id: "ty" });

// Retrieve relevant memories
const memories = await client.search("CSS preferences", { user_id: "ty" });

3. Better File Structure (No Dependencies)

memory/
├── projects/
│   ├── strykr.md
│   └── taska.md
├── people/
│   └── contacts.md
├── decisions/
│   └── 2026-01.md
├── lessons/
│   └── mistakes.md
└── preferences.md

Keep MEMORY.md as a summary (<5KB), link to detailed files.

Immediate Fixes Checklist

| Problem | Fix | |---------|-----| | Forgets preferences | Add ## Preferences section to MEMORY.md | | Repeats mistakes | Log every mistake to memory/lessons.md | | Sub-agents lack context | Include key context in spawn task prompt | | Forgets recent work | Strict daily file discipline | | Memory search not working | Check OPENAI_API_KEY is set |

Troubleshooting

Agent keeps forgetting mid-conversation: → SESSION-STATE.md not being updated. Check WAL protocol.

Irrelevant memories injected: → Disable autoCapture, increase minImportance threshold.

Memory too large, slow recall: → Run hygiene: clear old vectors, archive daily logs.

Git-Notes not persisting: → Run git notes push to sync with remote.

memory_search returns nothing: → Check OpenAI API key: echo $OPENAI_API_KEY → Verify memorySearch enabled in openclaw.json

---

Links

• bulletproof-memory: https://clawdhub.com/skills/bulletproof-memory
• lancedb-memory: https://clawdhub.com/skills/lancedb-memory
• git-notes-memory: https://clawdhub.com/skills/git-notes-memory
• memory-hygiene: https://clawdhub.com/skills/memory-hygiene
• supermemory: https://clawdhub.com/skills/supermemory

---

Built by @NextXFrontier — Part of the Next Frontier AI toolkit

File v1.2.2:README.md

Elite Longterm Memory 🧠

The ultimate memory system for AI agents. Never lose context again.

---

Works With

<p align="center"> <img src="https://img.shields.io/badge/Claude-AI-orange?style=for-the-badge&logo=anthropic" alt="Claude AI" /> <img src="https://img.shields.io/badge/GPT-OpenAI-412991?style=for-the-badge&logo=openai" alt="GPT" /> <img src="https://img.shields.io/badge/Cursor-IDE-000000?style=for-the-badge" alt="Cursor" /> <img src="https://img.shields.io/badge/LangChain-Framework-1C3C3C?style=for-the-badge" alt="LangChain" /> </p> <p align="center"> <strong>Built for:</strong> Clawdbot • Moltbot • Claude Code • Any AI Agent </p>

---

Combines 7 proven memory approaches into one bulletproof architecture:

• ✅ Bulletproof WAL Protocol — Write-ahead logging survives compaction
• ✅ LanceDB Vector Search — Semantic recall of relevant memories
• ✅ Git-Notes Knowledge Graph — Structured decisions, branch-aware
• ✅ File-Based Archives — Human-readable MEMORY.md + daily logs
• ✅ Cloud Backup — Optional SuperMemory sync
• ✅ Memory Hygiene — Keep vectors lean, prevent token waste
• ✅ Mem0 Auto-Extraction — Automatic fact extraction, 80% token reduction

Quick Start

# Initialize in your workspace
npx elite-longterm-memory init

# Check status
npx elite-longterm-memory status

# Create today's log
npx elite-longterm-memory today

Architecture

┌─────────────────────────────────────────────────────┐
│              ELITE LONGTERM MEMORY                  │
├─────────────────────────────────────────────────────┤
│  HOT RAM          WARM STORE        COLD STORE     │
│  SESSION-STATE.md → LanceDB      → Git-Notes       │
│  (survives         (semantic       (permanent      │
│   compaction)       search)         decisions)     │
│         │              │                │          │
│         └──────────────┼────────────────┘          │
│                        ▼                           │
│                   MEMORY.md                        │
│               (curated archive)                    │
└─────────────────────────────────────────────────────┘

The 5 Memory Layers

| Layer | File/System | Purpose | Persistence | |-------|-------------|---------|-------------| | 1. Hot RAM | SESSION-STATE.md | Active task context | Survives compaction | | 2. Warm Store | LanceDB | Semantic search | Auto-recall | | 3. Cold Store | Git-Notes | Structured decisions | Permanent | | 4. Archive | MEMORY.md + daily/ | Human-readable | Curated | | 5. Cloud | SuperMemory | Cross-device sync | Optional |

The WAL Protocol

Critical insight: Write state BEFORE responding, not after.

User: "Let's use Tailwind for this project"

Agent (internal):
1. Write to SESSION-STATE.md → "Decision: Use Tailwind"
2. THEN respond → "Got it — Tailwind it is..."

If you respond first and crash before saving, context is lost. WAL ensures durability.

Why Memory Fails (And How to Fix It)

| Problem | Cause | Fix | |---------|-------|-----| | Forgets everything | memory_search disabled | Enable + add OpenAI key | | Repeats mistakes | Lessons not logged | Write to memory/lessons.md | | Sub-agents isolated | No context inheritance | Pass context in task prompt | | Facts not captured | No auto-extraction | Use Mem0 (see below) |

Mem0 Integration (Recommended)

Auto-extract facts from conversations. 80% token reduction.

npm install mem0ai
export MEM0_API_KEY="your-key"

const { MemoryClient } = require('mem0ai');
const client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });

// Auto-extracts facts from messages
await client.add(messages, { user_id: "user123" });

// Retrieve relevant memories  
const memories = await client.search(query, { user_id: "user123" });

For Clawdbot/Moltbot Users

Add to ~/.clawdbot/clawdbot.json:

{
  "memorySearch": {
    "enabled": true,
    "provider": "openai",
    "sources": ["memory"]
  }
}

Files Created

workspace/
├── SESSION-STATE.md    # Hot RAM (active context)
├── MEMORY.md           # Curated long-term memory
└── memory/
    ├── 2026-01-30.md   # Daily logs
    └── ...

Commands

elite-memory init      # Initialize memory system
elite-memory status    # Check health
elite-memory today     # Create today's log
elite-memory help      # Show help

Links

• Full Documentation (SKILL.md)
• ClawdHub
• GitHub

---

Built by @NextXFrontier

File v1.2.2:_meta.json

{ "ownerId": "kn7ewywaj7mf48drbjw1baa5298016yv", "slug": "elite-longterm-memory", "version": "1.2.2", "publishedAt": 1770220745664 }

File v1.2.2:package.json

{ "name": "elite-longterm-memory", "version": "1.2.2", "description": "Ultimate AI agent memory system. Combines bulletproof WAL protocol, vector search, git-based knowledge graphs, cloud backup, and maintenance hygiene. Never lose context again.", "keywords": [ "memory", "ai-agent", "long-term-memory", "vector-search", "lancedb", "git-notes", "wal", "persistent-context", "claude", "gpt", "openclaw", "moltbot", "openclaw", "cursor", "copilot", "ai", "llm", "automation", "context-management", "mem0", "auto-extraction", "fact-extraction" ], "optionalDependencies": { "mem0ai": "^1.0.0" }, "author": "NextFrontierBuilds", "license": "MIT", "repository": { "type": "git", "url": "https://github.com/NextFrontierBuilds/elite-longterm-memory" }, "homepage": "https://github.com/NextFrontierBuilds/elite-longterm-memory", "bugs": { "url": "https://github.com/NextFrontierBuilds/elite-longterm-memory/issues" }, "bin": { "elite-memory": "./bin/elite-memory.js" }, "files": [ "SKILL.md", "bin/", "templates/", "README.md" ] }

Archive v1.2.1: 5 files, 9450 bytes

Files: bin/elite-memory.js (4875b), package.json (1179b), README.md (5593b), SKILL.md (12634b), _meta.json (140b)

File v1.2.1:SKILL.md

---

name: elite-longterm-memory version: 1.2.1 description: "Ultimate AI agent memory system. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Works with Claude, Cursor, GPT, Clawdbot agents." author: NextFrontierBuilds keywords: [memory, ai-agent, ai-coding, long-term-memory, vector-search, lancedb, git-notes, wal, persistent-context, claude, claude-code, gpt, cursor, copilot, clawdbot, moltbot, openclaw, vibe-coding, agentic] metadata: clawdbot: emoji: "🧠" requires: env: - OPENAI_API_KEY plugins: - memory-lancedb

Elite Longterm Memory 🧠

The ultimate memory system for AI agents. Combines 6 proven approaches into one bulletproof architecture.

Never lose context. Never forget decisions. Never repeat mistakes.

Architecture Overview

┌─────────────────────────────────────────────────────────────────┐
│                    ELITE LONGTERM MEMORY                        │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐             │
│  │   HOT RAM   │  │  WARM STORE │  │  COLD STORE │             │
│  │             │  │             │  │             │             │
│  │ SESSION-    │  │  LanceDB    │  │  Git-Notes  │             │
│  │ STATE.md    │  │  Vectors    │  │  Knowledge  │             │
│  │             │  │             │  │  Graph      │             │
│  │ (survives   │  │ (semantic   │  │ (permanent  │             │
│  │  compaction)│  │  search)    │  │  decisions) │             │
│  └─────────────┘  └─────────────┘  └─────────────┘             │
│         │                │                │                     │
│         └────────────────┼────────────────┘                     │
│                          ▼                                      │
│                  ┌─────────────┐                                │
│                  │  MEMORY.md  │  ← Curated long-term           │
│                  │  + daily/   │    (human-readable)            │
│                  └─────────────┘                                │
│                          │                                      │
│                          ▼                                      │
│                  ┌─────────────┐                                │
│                  │ SuperMemory │  ← Cloud backup (optional)     │
│                  │    API      │                                │
│                  └─────────────┘                                │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

The 5 Memory Layers

Layer 1: HOT RAM (SESSION-STATE.md)

From: bulletproof-memory

Active working memory that survives compaction. Write-Ahead Log protocol.

# SESSION-STATE.md — Active Working Memory

## Current Task
[What we're working on RIGHT NOW]

## Key Context
- User preference: ...
- Decision made: ...
- Blocker: ...

## Pending Actions
- [ ] ...

Rule: Write BEFORE responding. Triggered by user input, not agent memory.

Layer 2: WARM STORE (LanceDB Vectors)

From: lancedb-memory

Semantic search across all memories. Auto-recall injects relevant context.

# Auto-recall (happens automatically)
memory_recall query="project status" limit=5

# Manual store
memory_store text="User prefers dark mode" category="preference" importance=0.9

Layer 3: COLD STORE (Git-Notes Knowledge Graph)

From: git-notes-memory

Structured decisions, learnings, and context. Branch-aware.

# Store a decision (SILENT - never announce)
python3 memory.py -p $DIR remember '{"type":"decision","content":"Use React for frontend"}' -t tech -i h

# Retrieve context
python3 memory.py -p $DIR get "frontend"

Layer 4: CURATED ARCHIVE (MEMORY.md + daily/)

From: Clawdbot native

Human-readable long-term memory. Daily logs + distilled wisdom.

workspace/
├── MEMORY.md              # Curated long-term (the good stuff)
└── memory/
    ├── 2026-01-30.md      # Daily log
    ├── 2026-01-29.md
    └── topics/            # Topic-specific files

Layer 5: CLOUD BACKUP (SuperMemory) — Optional

From: supermemory

Cross-device sync. Chat with your knowledge base.

export SUPERMEMORY_API_KEY="your-key"
supermemory add "Important context"
supermemory search "what did we decide about..."

Layer 6: AUTO-EXTRACTION (Mem0) — Recommended

NEW: Automatic fact extraction

Mem0 automatically extracts facts from conversations. 80% token reduction.

npm install mem0ai
export MEM0_API_KEY="your-key"

const { MemoryClient } = require('mem0ai');
const client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });

// Conversations auto-extract facts
await client.add(messages, { user_id: "user123" });

// Retrieve relevant memories
const memories = await client.search(query, { user_id: "user123" });

Benefits:

• Auto-extracts preferences, decisions, facts
• Deduplicates and updates existing memories
• 80% reduction in tokens vs raw history
• Works across sessions automatically

Quick Setup

1. Create SESSION-STATE.md (Hot RAM)

cat > SESSION-STATE.md << 'EOF'
# SESSION-STATE.md — Active Working Memory

This file is the agent's "RAM" — survives compaction, restarts, distractions.

## Current Task
[None]

## Key Context
[None yet]

## Pending Actions
- [ ] None

## Recent Decisions
[None yet]

---
*Last updated: [timestamp]*
EOF

2. Enable LanceDB (Warm Store)

In ~/.clawdbot/clawdbot.json:

{
  "memorySearch": {
    "enabled": true,
    "provider": "openai",
    "sources": ["memory"],
    "minScore": 0.3,
    "maxResults": 10
  },
  "plugins": {
    "entries": {
      "memory-lancedb": {
        "enabled": true,
        "config": {
          "autoCapture": false,
          "autoRecall": true,
          "captureCategories": ["preference", "decision", "fact"],
          "minImportance": 0.7
        }
      }
    }
  }
}

3. Initialize Git-Notes (Cold Store)

cd ~/clawd
git init  # if not already
python3 skills/git-notes-memory/memory.py -p . sync --start

4. Verify MEMORY.md Structure

# Ensure you have:
# - MEMORY.md in workspace root
# - memory/ folder for daily logs
mkdir -p memory

5. (Optional) Setup SuperMemory

export SUPERMEMORY_API_KEY="your-key"
# Add to ~/.zshrc for persistence

Agent Instructions

On Session Start

1. Read SESSION-STATE.md — this is your hot context
2. Run memory_search for relevant prior context
3. Check memory/YYYY-MM-DD.md for recent activity

During Conversation

1. User gives concrete detail? → Write to SESSION-STATE.md BEFORE responding
2. Important decision made? → Store in Git-Notes (SILENTLY)
3. Preference expressed? → memory_store with importance=0.9

On Session End

1. Update SESSION-STATE.md with final state
2. Move significant items to MEMORY.md if worth keeping long-term
3. Create/update daily log in memory/YYYY-MM-DD.md

Memory Hygiene (Weekly)

1. Review SESSION-STATE.md — archive completed tasks
2. Check LanceDB for junk: memory_recall query="*" limit=50
3. Clear irrelevant vectors: memory_forget id=<id>
4. Consolidate daily logs into MEMORY.md

The WAL Protocol (Critical)

Write-Ahead Log: Write state BEFORE responding, not after.

| Trigger | Action | |---------|--------| | User states preference | Write to SESSION-STATE.md → then respond | | User makes decision | Write to SESSION-STATE.md → then respond | | User gives deadline | Write to SESSION-STATE.md → then respond | | User corrects you | Write to SESSION-STATE.md → then respond |

Why? If you respond first and crash/compact before saving, context is lost. WAL ensures durability.

Example Workflow

User: "Let's use Tailwind for this project, not vanilla CSS"

Agent (internal):
1. Write to SESSION-STATE.md: "Decision: Use Tailwind, not vanilla CSS"
2. Store in Git-Notes: decision about CSS framework
3. memory_store: "User prefers Tailwind over vanilla CSS" importance=0.9
4. THEN respond: "Got it — Tailwind it is..."

Maintenance Commands

# Audit vector memory
memory_recall query="*" limit=50

# Clear all vectors (nuclear option)
rm -rf ~/.clawdbot/memory/lancedb/
clawdbot gateway restart

# Export Git-Notes
python3 memory.py -p . export --format json > memories.json

# Check memory health
du -sh ~/.clawdbot/memory/
wc -l MEMORY.md
ls -la memory/

Why Memory Fails

Understanding the root causes helps you fix them:

| Failure Mode | Cause | Fix | |--------------|-------|-----| | Forgets everything | memory_search disabled | Enable + add OpenAI key | | Files not loaded | Agent skips reading memory | Add to AGENTS.md rules | | Facts not captured | No auto-extraction | Use Mem0 or manual logging | | Sub-agents isolated | Don't inherit context | Pass context in task prompt | | Repeats mistakes | Lessons not logged | Write to memory/lessons.md |

Solutions (Ranked by Effort)

1. Quick Win: Enable memory_search

If you have an OpenAI key, enable semantic search:

clawdbot configure --section web

This enables vector search over MEMORY.md + memory/*.md files.

2. Recommended: Mem0 Integration

Auto-extract facts from conversations. 80% token reduction.

npm install mem0ai

const { MemoryClient } = require('mem0ai');

const client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });

// Auto-extract and store
await client.add([
  { role: "user", content: "I prefer Tailwind over vanilla CSS" }
], { user_id: "ty" });

// Retrieve relevant memories
const memories = await client.search("CSS preferences", { user_id: "ty" });

3. Better File Structure (No Dependencies)

memory/
├── projects/
│   ├── strykr.md
│   └── taska.md
├── people/
│   └── contacts.md
├── decisions/
│   └── 2026-01.md
├── lessons/
│   └── mistakes.md
└── preferences.md

Keep MEMORY.md as a summary (<5KB), link to detailed files.

Immediate Fixes Checklist

| Problem | Fix | |---------|-----| | Forgets preferences | Add ## Preferences section to MEMORY.md | | Repeats mistakes | Log every mistake to memory/lessons.md | | Sub-agents lack context | Include key context in spawn task prompt | | Forgets recent work | Strict daily file discipline | | Memory search not working | Check OPENAI_API_KEY is set |

Troubleshooting

Agent keeps forgetting mid-conversation: → SESSION-STATE.md not being updated. Check WAL protocol.

Irrelevant memories injected: → Disable autoCapture, increase minImportance threshold.

Memory too large, slow recall: → Run hygiene: clear old vectors, archive daily logs.

Git-Notes not persisting: → Run git notes push to sync with remote.

memory_search returns nothing: → Check OpenAI API key: echo $OPENAI_API_KEY → Verify memorySearch enabled in clawdbot.json

---

Links

• bulletproof-memory: https://clawdhub.com/skills/bulletproof-memory
• lancedb-memory: https://clawdhub.com/skills/lancedb-memory
• git-notes-memory: https://clawdhub.com/skills/git-notes-memory
• memory-hygiene: https://clawdhub.com/skills/memory-hygiene
• supermemory: https://clawdhub.com/skills/supermemory

---

Built by @NextXFrontier — Part of the Next Frontier AI toolkit

File v1.2.1:README.md

Elite Longterm Memory 🧠

The ultimate memory system for AI agents. Never lose context again.

---

Works With

<p align="center"> <img src="https://img.shields.io/badge/Claude-AI-orange?style=for-the-badge&logo=anthropic" alt="Claude AI" /> <img src="https://img.shields.io/badge/GPT-OpenAI-412991?style=for-the-badge&logo=openai" alt="GPT" /> <img src="https://img.shields.io/badge/Cursor-IDE-000000?style=for-the-badge" alt="Cursor" /> <img src="https://img.shields.io/badge/LangChain-Framework-1C3C3C?style=for-the-badge" alt="LangChain" /> </p> <p align="center"> <strong>Built for:</strong> Clawdbot • Moltbot • Claude Code • Any AI Agent </p>

---

Combines 7 proven memory approaches into one bulletproof architecture:

• ✅ Bulletproof WAL Protocol — Write-ahead logging survives compaction
• ✅ LanceDB Vector Search — Semantic recall of relevant memories
• ✅ Git-Notes Knowledge Graph — Structured decisions, branch-aware
• ✅ File-Based Archives — Human-readable MEMORY.md + daily logs
• ✅ Cloud Backup — Optional SuperMemory sync
• ✅ Memory Hygiene — Keep vectors lean, prevent token waste
• ✅ Mem0 Auto-Extraction — Automatic fact extraction, 80% token reduction

Quick Start

# Initialize in your workspace
npx elite-longterm-memory init

# Check status
npx elite-longterm-memory status

# Create today's log
npx elite-longterm-memory today

Architecture

┌─────────────────────────────────────────────────────┐
│              ELITE LONGTERM MEMORY                  │
├─────────────────────────────────────────────────────┤
│  HOT RAM          WARM STORE        COLD STORE     │
│  SESSION-STATE.md → LanceDB      → Git-Notes       │
│  (survives         (semantic       (permanent      │
│   compaction)       search)         decisions)     │
│         │              │                │          │
│         └──────────────┼────────────────┘          │
│                        ▼                           │
│                   MEMORY.md                        │
│               (curated archive)                    │
└─────────────────────────────────────────────────────┘

The 5 Memory Layers

| Layer | File/System | Purpose | Persistence | |-------|-------------|---------|-------------| | 1. Hot RAM | SESSION-STATE.md | Active task context | Survives compaction | | 2. Warm Store | LanceDB | Semantic search | Auto-recall | | 3. Cold Store | Git-Notes | Structured decisions | Permanent | | 4. Archive | MEMORY.md + daily/ | Human-readable | Curated | | 5. Cloud | SuperMemory | Cross-device sync | Optional |

The WAL Protocol

Critical insight: Write state BEFORE responding, not after.

User: "Let's use Tailwind for this project"

Agent (internal):
1. Write to SESSION-STATE.md → "Decision: Use Tailwind"
2. THEN respond → "Got it — Tailwind it is..."

If you respond first and crash before saving, context is lost. WAL ensures durability.

Why Memory Fails (And How to Fix It)

| Problem | Cause | Fix | |---------|-------|-----| | Forgets everything | memory_search disabled | Enable + add OpenAI key | | Repeats mistakes | Lessons not logged | Write to memory/lessons.md | | Sub-agents isolated | No context inheritance | Pass context in task prompt | | Facts not captured | No auto-extraction | Use Mem0 (see below) |

Mem0 Integration (Recommended)

Auto-extract facts from conversations. 80% token reduction.

npm install mem0ai
export MEM0_API_KEY="your-key"

const { MemoryClient } = require('mem0ai');
const client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });

// Auto-extracts facts from messages
await client.add(messages, { user_id: "user123" });

// Retrieve relevant memories  
const memories = await client.search(query, { user_id: "user123" });

For Clawdbot/Moltbot Users

Add to ~/.clawdbot/clawdbot.json:

{
  "memorySearch": {
    "enabled": true,
    "provider": "openai",
    "sources": ["memory"]
  }
}

Files Created

workspace/
├── SESSION-STATE.md    # Hot RAM (active context)
├── MEMORY.md           # Curated long-term memory
└── memory/
    ├── 2026-01-30.md   # Daily logs
    └── ...

Commands

elite-memory init      # Initialize memory system
elite-memory status    # Check health
elite-memory today     # Create today's log
elite-memory help      # Show help

Links

• Full Documentation (SKILL.md)
• ClawdHub
• GitHub

---

Built by @NextXFrontier

File v1.2.1:_meta.json

{ "ownerId": "kn7ewywaj7mf48drbjw1baa5298016yv", "slug": "elite-longterm-memory", "version": "1.2.1", "publishedAt": 1770219845285 }

File v1.2.1:package.json

{ "name": "elite-longterm-memory", "version": "1.2.0", "description": "Ultimate AI agent memory system. Combines bulletproof WAL protocol, vector search, git-based knowledge graphs, cloud backup, and maintenance hygiene. Never lose context again.", "keywords": [ "memory", "ai-agent", "long-term-memory", "vector-search", "lancedb", "git-notes", "wal", "persistent-context", "claude", "gpt", "clawdbot", "moltbot", "openclaw", "cursor", "copilot", "ai", "llm", "automation", "context-management", "mem0", "auto-extraction", "fact-extraction" ], "optionalDependencies": { "mem0ai": "^1.0.0" }, "author": "NextFrontierBuilds", "license": "MIT", "repository": { "type": "git", "url": "https://github.com/NextFrontierBuilds/elite-longterm-memory" }, "homepage": "https://github.com/NextFrontierBuilds/elite-longterm-memory", "bugs": { "url": "https://github.com/NextFrontierBuilds/elite-longterm-memory/issues" }, "bin": { "elite-memory": "./bin/elite-memory.js" }, "files": [ "SKILL.md", "bin/", "templates/", "README.md" ] }

Archive v0.1.0: 5 files, 9422 bytes

Files: bin/elite-memory.js (4875b), package.json (1167b), README.md (5593b), SKILL.md (12615b), _meta.json (140b)

File v0.1.0:SKILL.md

---

name: elite-longterm-memory version: 1.2.0 description: "Ultimate AI agent memory system. Combines bulletproof WAL protocol, vector search, git-based knowledge graphs, cloud backup, and maintenance hygiene. Never lose context again. For Clawdbot, Moltbot, Claude, GPT agents." author: NextFrontierBuilds keywords: [memory, ai-agent, long-term-memory, vector-search, lancedb, git-notes, wal, persistent-context, claude, gpt, clawdbot, moltbot] metadata: clawdbot: emoji: "🧠" requires: env: - OPENAI_API_KEY plugins: - memory-lancedb

Elite Longterm Memory 🧠

The ultimate memory system for AI agents. Combines 6 proven approaches into one bulletproof architecture.

Never lose context. Never forget decisions. Never repeat mistakes.

Architecture Overview

┌─────────────────────────────────────────────────────────────────┐
│                    ELITE LONGTERM MEMORY                        │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐             │
│  │   HOT RAM   │  │  WARM STORE │  │  COLD STORE │             │
│  │             │  │             │  │             │             │
│  │ SESSION-    │  │  LanceDB    │  │  Git-Notes  │             │
│  │ STATE.md    │  │  Vectors    │  │  Knowledge  │             │
│  │             │  │             │  │  Graph      │             │
│  │ (survives   │  │ (semantic   │  │ (permanent  │             │
│  │  compaction)│  │  search)    │  │  decisions) │             │
│  └─────────────┘  └─────────────┘  └─────────────┘             │
│         │                │                │                     │
│         └────────────────┼────────────────┘                     │
│                          ▼                                      │
│                  ┌─────────────┐                                │
│                  │  MEMORY.md  │  ← Curated long-term           │
│                  │  + daily/   │    (human-readable)            │
│                  └─────────────┘                                │
│                          │                                      │
│                          ▼                                      │
│                  ┌─────────────┐                                │
│                  │ SuperMemory │  ← Cloud backup (optional)     │
│                  │    API      │                                │
│                  └─────────────┘                                │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

The 5 Memory Layers

Layer 1: HOT RAM (SESSION-STATE.md)

From: bulletproof-memory

Active working memory that survives compaction. Write-Ahead Log protocol.

# SESSION-STATE.md — Active Working Memory

## Current Task
[What we're working on RIGHT NOW]

## Key Context
- User preference: ...
- Decision made: ...
- Blocker: ...

## Pending Actions
- [ ] ...

Rule: Write BEFORE responding. Triggered by user input, not agent memory.

Layer 2: WARM STORE (LanceDB Vectors)

From: lancedb-memory

Semantic search across all memories. Auto-recall injects relevant context.

# Auto-recall (happens automatically)
memory_recall query="project status" limit=5

# Manual store
memory_store text="User prefers dark mode" category="preference" importance=0.9

Layer 3: COLD STORE (Git-Notes Knowledge Graph)

From: git-notes-memory

Structured decisions, learnings, and context. Branch-aware.

# Store a decision (SILENT - never announce)
python3 memory.py -p $DIR remember '{"type":"decision","content":"Use React for frontend"}' -t tech -i h

# Retrieve context
python3 memory.py -p $DIR get "frontend"

Layer 4: CURATED ARCHIVE (MEMORY.md + daily/)

From: Clawdbot native

Human-readable long-term memory. Daily logs + distilled wisdom.

workspace/
├── MEMORY.md              # Curated long-term (the good stuff)
└── memory/
    ├── 2026-01-30.md      # Daily log
    ├── 2026-01-29.md
    └── topics/            # Topic-specific files

Layer 5: CLOUD BACKUP (SuperMemory) — Optional

From: supermemory

Cross-device sync. Chat with your knowledge base.

export SUPERMEMORY_API_KEY="your-key"
supermemory add "Important context"
supermemory search "what did we decide about..."

Layer 6: AUTO-EXTRACTION (Mem0) — Recommended

NEW: Automatic fact extraction

Mem0 automatically extracts facts from conversations. 80% token reduction.

npm install mem0ai
export MEM0_API_KEY="your-key"

const { MemoryClient } = require('mem0ai');
const client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });

// Conversations auto-extract facts
await client.add(messages, { user_id: "user123" });

// Retrieve relevant memories
const memories = await client.search(query, { user_id: "user123" });

Benefits:

• Auto-extracts preferences, decisions, facts
• Deduplicates and updates existing memories
• 80% reduction in tokens vs raw history
• Works across sessions automatically

Quick Setup

1. Create SESSION-STATE.md (Hot RAM)

cat > SESSION-STATE.md << 'EOF'
# SESSION-STATE.md — Active Working Memory

This file is the agent's "RAM" — survives compaction, restarts, distractions.

## Current Task
[None]

## Key Context
[None yet]

## Pending Actions
- [ ] None

## Recent Decisions
[None yet]

---
*Last updated: [timestamp]*
EOF

2. Enable LanceDB (Warm Store)

In ~/.clawdbot/clawdbot.json:

{
  "memorySearch": {
    "enabled": true,
    "provider": "openai",
    "sources": ["memory"],
    "minScore": 0.3,
    "maxResults": 10
  },
  "plugins": {
    "entries": {
      "memory-lancedb": {
        "enabled": true,
        "config": {
          "autoCapture": false,
          "autoRecall": true,
          "captureCategories": ["preference", "decision", "fact"],
          "minImportance": 0.7
        }
      }
    }
  }
}

3. Initialize Git-Notes (Cold Store)

cd ~/clawd
git init  # if not already
python3 skills/git-notes-memory/memory.py -p . sync --start

4. Verify MEMORY.md Structure

# Ensure you have:
# - MEMORY.md in workspace root
# - memory/ folder for daily logs
mkdir -p memory

5. (Optional) Setup SuperMemory

export SUPERMEMORY_API_KEY="your-key"
# Add to ~/.zshrc for persistence

Agent Instructions

On Session Start

1. Read SESSION-STATE.md — this is your hot context
2. Run memory_search for relevant prior context
3. Check memory/YYYY-MM-DD.md for recent activity

During Conversation

1. User gives concrete detail? → Write to SESSION-STATE.md BEFORE responding
2. Important decision made? → Store in Git-Notes (SILENTLY)
3. Preference expressed? → memory_store with importance=0.9

On Session End

1. Update SESSION-STATE.md with final state
2. Move significant items to MEMORY.md if worth keeping long-term
3. Create/update daily log in memory/YYYY-MM-DD.md

Memory Hygiene (Weekly)

1. Review SESSION-STATE.md — archive completed tasks
2. Check LanceDB for junk: memory_recall query="*" limit=50
3. Clear irrelevant vectors: memory_forget id=<id>
4. Consolidate daily logs into MEMORY.md

The WAL Protocol (Critical)

Write-Ahead Log: Write state BEFORE responding, not after.

| Trigger | Action | |---------|--------| | User states preference | Write to SESSION-STATE.md → then respond | | User makes decision | Write to SESSION-STATE.md → then respond | | User gives deadline | Write to SESSION-STATE.md → then respond | | User corrects you | Write to SESSION-STATE.md → then respond |

Why? If you respond first and crash/compact before saving, context is lost. WAL ensures durability.

Example Workflow

User: "Let's use Tailwind for this project, not vanilla CSS"

Agent (internal):
1. Write to SESSION-STATE.md: "Decision: Use Tailwind, not vanilla CSS"
2. Store in Git-Notes: decision about CSS framework
3. memory_store: "User prefers Tailwind over vanilla CSS" importance=0.9
4. THEN respond: "Got it — Tailwind it is..."

Maintenance Commands

# Audit vector memory
memory_recall query="*" limit=50

# Clear all vectors (nuclear option)
rm -rf ~/.clawdbot/memory/lancedb/
clawdbot gateway restart

# Export Git-Notes
python3 memory.py -p . export --format json > memories.json

# Check memory health
du -sh ~/.clawdbot/memory/
wc -l MEMORY.md
ls -la memory/

Why Memory Fails

Understanding the root causes helps you fix them:

| Failure Mode | Cause | Fix | |--------------|-------|-----| | Forgets everything | memory_search disabled | Enable + add OpenAI key | | Files not loaded | Agent skips reading memory | Add to AGENTS.md rules | | Facts not captured | No auto-extraction | Use Mem0 or manual logging | | Sub-agents isolated | Don't inherit context | Pass context in task prompt | | Repeats mistakes | Lessons not logged | Write to memory/lessons.md |

Solutions (Ranked by Effort)

1. Quick Win: Enable memory_search

If you have an OpenAI key, enable semantic search:

clawdbot configure --section web

This enables vector search over MEMORY.md + memory/*.md files.

2. Recommended: Mem0 Integration

Auto-extract facts from conversations. 80% token reduction.

npm install mem0ai

const { MemoryClient } = require('mem0ai');

const client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });

// Auto-extract and store
await client.add([
  { role: "user", content: "I prefer Tailwind over vanilla CSS" }
], { user_id: "ty" });

// Retrieve relevant memories
const memories = await client.search("CSS preferences", { user_id: "ty" });

3. Better File Structure (No Dependencies)

memory/
├── projects/
│   ├── strykr.md
│   └── taska.md
├── people/
│   └── contacts.md
├── decisions/
│   └── 2026-01.md
├── lessons/
│   └── mistakes.md
└── preferences.md

Keep MEMORY.md as a summary (<5KB), link to detailed files.

Immediate Fixes Checklist

| Problem | Fix | |---------|-----| | Forgets preferences | Add ## Preferences section to MEMORY.md | | Repeats mistakes | Log every mistake to memory/lessons.md | | Sub-agents lack context | Include key context in spawn task prompt | | Forgets recent work | Strict daily file discipline | | Memory search not working | Check OPENAI_API_KEY is set |

Troubleshooting

Agent keeps forgetting mid-conversation: → SESSION-STATE.md not being updated. Check WAL protocol.

Irrelevant memories injected: → Disable autoCapture, increase minImportance threshold.

Memory too large, slow recall: → Run hygiene: clear old vectors, archive daily logs.

Git-Notes not persisting: → Run git notes push to sync with remote.

memory_search returns nothing: → Check OpenAI API key: echo $OPENAI_API_KEY → Verify memorySearch enabled in clawdbot.json

---

Links

• bulletproof-memory: https://clawdhub.com/skills/bulletproof-memory
• lancedb-memory: https://clawdhub.com/skills/lancedb-memory
• git-notes-memory: https://clawdhub.com/skills/git-notes-memory
• memory-hygiene: https://clawdhub.com/skills/memory-hygiene
• supermemory: https://clawdhub.com/skills/supermemory

---

Built by @NextXFrontier — Part of the Next Frontier AI toolkit

File v0.1.0:README.md

Elite Longterm Memory 🧠

The ultimate memory system for AI agents. Never lose context again.

---

Works With

<p align="center"> <img src="https://img.shields.io/badge/Claude-AI-orange?style=for-the-badge&logo=anthropic" alt="Claude AI" /> <img src="https://img.shields.io/badge/GPT-OpenAI-412991?style=for-the-badge&logo=openai" alt="GPT" /> <img src="https://img.shields.io/badge/Cursor-IDE-000000?style=for-the-badge" alt="Cursor" /> <img src="https://img.shields.io/badge/LangChain-Framework-1C3C3C?style=for-the-badge" alt="LangChain" /> </p> <p align="center"> <strong>Built for:</strong> Clawdbot • Moltbot • Claude Code • Any AI Agent </p>

---

Combines 7 proven memory approaches into one bulletproof architecture:

• ✅ Bulletproof WAL Protocol — Write-ahead logging survives compaction
• ✅ LanceDB Vector Search — Semantic recall of relevant memories
• ✅ Git-Notes Knowledge Graph — Structured decisions, branch-aware
• ✅ File-Based Archives — Human-readable MEMORY.md + daily logs
• ✅ Cloud Backup — Optional SuperMemory sync
• ✅ Memory Hygiene — Keep vectors lean, prevent token waste
• ✅ Mem0 Auto-Extraction — Automatic fact extraction, 80% token reduction

Quick Start

# Initialize in your workspace
npx elite-longterm-memory init

# Check status
npx elite-longterm-memory status

# Create today's log
npx elite-longterm-memory today

Architecture

┌─────────────────────────────────────────────────────┐
│              ELITE LONGTERM MEMORY                  │
├─────────────────────────────────────────────────────┤
│  HOT RAM          WARM STORE        COLD STORE     │
│  SESSION-STATE.md → LanceDB      → Git-Notes       │
│  (survives         (semantic       (permanent      │
│   compaction)       search)         decisions)     │
│         │              │                │          │
│         └──────────────┼────────────────┘          │
│                        ▼                           │
│                   MEMORY.md                        │
│               (curated archive)                    │
└─────────────────────────────────────────────────────┘

The 5 Memory Layers

| Layer | File/System | Purpose | Persistence | |-------|-------------|---------|-------------| | 1. Hot RAM | SESSION-STATE.md | Active task context | Survives compaction | | 2. Warm Store | LanceDB | Semantic search | Auto-recall | | 3. Cold Store | Git-Notes | Structured decisions | Permanent | | 4. Archive | MEMORY.md + daily/ | Human-readable | Curated | | 5. Cloud | SuperMemory | Cross-device sync | Optional |

The WAL Protocol

Critical insight: Write state BEFORE responding, not after.

User: "Let's use Tailwind for this project"

Agent (internal):
1. Write to SESSION-STATE.md → "Decision: Use Tailwind"
2. THEN respond → "Got it — Tailwind it is..."

If you respond first and crash before saving, context is lost. WAL ensures durability.

Why Memory Fails (And How to Fix It)

| Problem | Cause | Fix | |---------|-------|-----| | Forgets everything | memory_search disabled | Enable + add OpenAI key | | Repeats mistakes | Lessons not logged | Write to memory/lessons.md | | Sub-agents isolated | No context inheritance | Pass context in task prompt | | Facts not captured | No auto-extraction | Use Mem0 (see below) |

Mem0 Integration (Recommended)

Auto-extract facts from conversations. 80% token reduction.

npm install mem0ai
export MEM0_API_KEY="your-key"

const { MemoryClient } = require('mem0ai');
const client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });

// Auto-extracts facts from messages
await client.add(messages, { user_id: "user123" });

// Retrieve relevant memories  
const memories = await client.search(query, { user_id: "user123" });

For Clawdbot/Moltbot Users

Add to ~/.clawdbot/clawdbot.json:

{
  "memorySearch": {
    "enabled": true,
    "provider": "openai",
    "sources": ["memory"]
  }
}

Files Created

workspace/
├── SESSION-STATE.md    # Hot RAM (active context)
├── MEMORY.md           # Curated long-term memory
└── memory/
    ├── 2026-01-30.md   # Daily logs
    └── ...

Commands

elite-memory init      # Initialize memory system
elite-memory status    # Check health
elite-memory today     # Create today's log
elite-memory help      # Show help

Links

• Full Documentation (SKILL.md)
• ClawdHub
• GitHub

---

Built by @NextXFrontier

File v0.1.0:_meta.json

{ "ownerId": "kn7ewywaj7mf48drbjw1baa5298016yv", "slug": "elite-longterm-memory", "version": "0.1.0", "publishedAt": 1770050243398 }

File v0.1.0:package.json

{ "name": "elite-longterm-memory", "version": "1.2.0", "description": "Ultimate AI agent memory system. Combines bulletproof WAL protocol, vector search, git-based knowledge graphs, cloud backup, and maintenance hygiene. Never lose context again.", "keywords": [ "memory", "ai-agent", "long-term-memory", "vector-search", "lancedb", "git-notes", "wal", "persistent-context", "claude", "gpt", "clawdbot", "moltbot", "cursor", "copilot", "ai", "llm", "automation", "context-management", "mem0", "auto-extraction", "fact-extraction" ], "optionalDependencies": { "mem0ai": "^1.0.0" }, "author": "NextFrontierBuilds", "license": "MIT", "repository": { "type": "git", "url": "https://github.com/NextFrontierBuilds/elite-longterm-memory" }, "homepage": "https://github.com/NextFrontierBuilds/elite-longterm-memory", "bugs": { "url": "https://github.com/NextFrontierBuilds/elite-longterm-memory/issues" }, "bin": { "elite-memory": "./bin/elite-memory.js" }, "files": [ "SKILL.md", "bin/", "templates/", "README.md" ] }