elite-longterm-memory

Ultimate AI agent memory system. Combines bulletproof WAL protocol, vector search, git-based knowledge graphs, cloud backup, and maintenance hygiene. Never l...

Security Scan

The skill appears to do what it claims (create and manage local memory files and recommend optional cloud integrations); it contains an innocuous CLI script and no obvious exfiltration, but it references additional optional third‑party API keys and packages that you should review before using.

Purpose & Capability

The name/description (long‑term memory for agents) aligns with the included files and instructions: templates for SESSION-STATE.md, MEMORY.md, daily logs, and guidance to enable LanceDB/mem0/SuperMemory. Requiring OPENAI_API_KEY to power semantic recall is reasonable. The skill also recommends optional services (MEM0, SuperMemory) and lists mem0ai as an optional dependency in package.json — these are explainable extensions, not mismatched requirements.

Instruction Scope

SKILL.md directs the agent/user to create and edit local files (SESSION-STATE.md, MEMORY.md, memory/...), to edit ~/.clawdbot/clawdbot.json, and to optionally export SUPERMEMORY_API_KEY and MEM0_API_KEY for cloud/auto‑extraction features. Instructions do not instruct reading arbitrary unrelated system files or exfiltrating secrets, but they do enable integrations with external services (mem0, SuperMemory) which would require you to supply additional API keys if you enable them. The SKILL.md refers to those env vars even though they are optional and not declared in the skill's required env list.

Install Mechanism

There is no install spec in the registry entry (instruction-only), which is lower risk. However the package includes a CLI script (bin/elite-memory.js) and package.json with an optional dependency (mem0ai). If you install/run this package (npx or npm), npm could fetch optional dependencies from the public registry. The provided bin script only writes/reads markdown files and checks a local LanceDB path — it does not perform network I/O itself.

Credentials

The registry requires only OPENAI_API_KEY (proportionate for semantic recall). SKILL.md and README also show optional SUPERMEMORY_API_KEY and MEM0_API_KEY for third‑party services; those are not declared as required, which is acceptable but worth noting because enabling those features would expose additional credentials to external services. No unrelated credentials or broad environment access are requested.

Persistence & Privilege

The skill does not request permanent 'always' inclusion and does not modify other skills' configuration. The CLI writes files within the current workspace and checks a user home path for LanceDB — normal behavior for a memory tool. Autonomous invocation (disable-model-invocation: false) is default platform behavior and not a unique concern here.

Assessment

What to consider before installing or running this skill: - It will create/edit files in whatever directory you run it from (SESSION-STATE.md, MEMORY.md, memory/). Run it in a workspace you control. - The skill only requires OPENAI_API_KEY, but it recommends optional integrations (Mem0, SuperMemory). Only provide those additional API keys if you trust the third‑party services and understand where data will be sent. - There is a small CLI (bin/elite-memory.js) included; inspect the script (it only writes/reads markdown and directories) before running. If you use npx/npm to install the package, npm may fetch optional dependencies from the public registry (mem0ai). - If you plan to enable cloud backup or auto‑extraction, read the privacy/security docs of those services to understand retention and access to your memory data. - Recommended safe steps: review the repository files locally, run the CLI in an isolated directory, and avoid supplying extra API keys unless you need the optional features.

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