Elite Longterm Memory 1.2.3

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

Security Scan

The skill mostly does what its README and SKILL.md claim (creates local memory files, recommends LanceDB/Mem0/SuperMemory integrations), but there are multiple metadata and requirement inconsistencies that merit caution before installing.

Purpose & Capability

Functionality (WAL file, MEMORY.md, daily logs, simple CLI) aligns with the described 'long-term memory' purpose. However the package/registry metadata is inconsistent (registry lists version 1.0.0 while package.json/SKILL.md show 1.2.3; ownerId values differ; registry lists no homepage but package.json contains a GitHub URL). The SKILL.md and README reference running npm and python3 and enabling a LanceDB plugin, but the declared required binaries list is empty — the skill includes a Node CLI, so node/npm should be declared. These mismatches suggest sloppy packaging or poor provenance.

Instruction Scope

Runtime instructions are largely scoped to creating and managing local files (SESSION-STATE.md, MEMORY.md, memory/*) and recommending configuration changes to agent config files (e.g., ~/.openclaw/openclaw.json or ~/.clawdbot/clawdbot.json). The docs also reference optional external services (SuperMemory, Mem0) and example commands that call python3 memory.py (a script not included in the bundle) and npm install mem0ai. The instructions therefore rely on external tooling and optional keys; they do not attempt to read unrelated system secrets, but they do instruct users to modify agent config files and to export API keys if they opt into cloud services.

Install Mechanism

There is no install spec (instruction-only), which reduces risk. The bundle includes a Node CLI (bin/elite-memory.js) and a package.json listing mem0ai as optionalDependency. Because the skill contains executable JS, installing or executing it (npx or node) will write files in the user's workspace. No downloads from arbitrary URLs are present in the bundle. Still, the presence of a CLI means the user should inspect the script before running it.

Credentials

Declared required env vars are limited to OPENAI_API_KEY, which is plausible for memory search/semantic recall. The SKILL.md and README mention additional optional keys (MEM0_API_KEY, SUPERMEMORY_API_KEY) for optional integrations; those are not required by default. No unrelated credentials (AWS, GitHub tokens, etc.) are requested. However, the skill references external services that would require more secrets only if the user opts in.

Persistence & Privilege

always is false and the skill does not request elevated platform privileges. The CLI only writes files into the current working directory and checks for a LanceDB path under HOME; it does not modify other skills or system-wide agent code by itself. The SKILL.md asks the user to edit agent config files if they want to enable the LanceDB plugin — it does not perform those edits automatically.

What to consider before installing

This skill appears to implement a local file-based memory system and a small Node CLI that initializes SESSION-STATE.md, MEMORY.md, and daily logs. Before installing or running it: 1) Verify the package provenance (registry metadata has mismatched version and ownerId vs package.json/_meta.json and homepage), and prefer an official GitHub/npm release if available. 2) Inspect bin/elite-memory.js yourself — it writes files in the working directory (benign for a memory tool) but it's executable JS so only run it if you trust the author. 3) Expect to need node/npm (and optionally python3) even though required binaries are not declared; ensure those tools are available. 4) Be cautious when enabling optional cloud features (Mem0, SuperMemory) — they require separate API keys and will send data to external services. Only provide keys you trust and understand what data will be uploaded. 5) If provenance is unclear, prefer to recreate the simple file templates yourself rather than running the CLI. These inconsistencies lower confidence in packaging quality; proceed only after manual review or obtaining the code from a verified upstream source.

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