memvault

Production-ready long-term memory server for AI agents with Ebbinghaus decay and strength-weighted retrieval. Use when you need persistent memory across agent sessions, memory decay (forgetting curve), memory statistics, or multi-agent memory tracking. Triggers: long-term memory, remember, recall, memory decay, Ebbinghaus, agent memory, memvault. Requires Docker.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "memvault" with this command: npx skills add wjy9902/memvault

MemVault — Long-term Memory for AI Agents

Quick Start

# Install (one command — Docker handles everything)
bash scripts/install.sh

# Verify
memvault health

Usage

# Store a memory
memvault memorize-text <user_id> "<message>" "[reply]"

# Retrieve memories (strength-weighted)
memvault retrieve <user_id> "<query>"

# Run daily decay (memories fade like human memory)
memvault decay <user_id>

# Check stats
memvault stats <user_id>

API Endpoints

MethodEndpointDescription
POST/memorizeStore conversation → extract facts/events/knowledge
POST/retrieveStrength-weighted vector search (similarity × strength)
POST/decayEbbinghaus forgetting curve (run daily via cron)
GET/statsMemory distribution, access patterns, agent breakdown
GET/healthService health

How It Works

  1. Store: Conversations → LLM extracts facts → embedded → stored in pgvector
  2. Retrieve: Query embedded → cosine similarity × memory strength → ranked results
  3. Decay: strength = exp(-rate × days / (1 + damping × ln(1 + access_count)))
  4. Access boost: Each retrieval increments access_count, slowing decay

Fading memories (strength < 0.1) are excluded from search.

Configuration

All via environment variables in .env (created by install script):

  • MEMVAULT_LLM_BASE_URL — Default: Ollama local. Set to OpenAI/Groq/etc URL if preferred
  • MEMVAULT_LLM_MODEL — Default: qwen2.5:3b
  • MEMVAULT_TRANSLATION — Set true + MEMVAULT_TRANSLATION_LANG for auto-translation
  • MEMVAULT_PORT — Default: 8002

Daily Cron Setup

Add Ebbinghaus decay to your agent's cron:

0 3 * * *  curl -s -X POST 'http://127.0.0.1:8002/decay?user_id=YOUR_USER_ID'

TOOLS.md Snippet

## MemVault 🧠
memvault memorize-text "<user_id>" "<content>" "<context>"
memvault retrieve "<user_id>" "<query>"
memvault decay <user_id>
memvault stats <user_id>
- API: 127.0.0.1:8002

Multi-Agent Memory

Tag memories by source agent:

curl -X POST http://localhost:8002/memorize -H "Content-Type: application/json" \
  -d '{"conversation": [
    {"role": "metadata", "content": "{\"source_agent\": \"research-bot\"}"},
    {"role": "user", "content": "Found new papers on transformers"}
  ], "user_id": "team"}'

Troubleshooting

  • "Connection refused" → Run docker compose -f ~/.openclaw/workspace/skills/memvault/docker-compose.yml up -d
  • Slow memorize → Normal, LLM extraction takes 5-15s per conversation
  • No results from retrieve → Check memvault stats — if total=0, nothing stored yet
  • All memories fading → Reduce decay_rate: curl -X POST 'http://localhost:8002/decay?decay_rate=0.05'

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

Memori

Agent-native memory for OpenClaw that structures memory from agent trace, execution history, decisions, tool calls, and conversations into durable long-term...

Registry SourceRecently Updated
5802Profile unavailable
Automation

Echo — Adopt an Echo. AI-Native Pet. 回声。Eco.

Adopt a virtual Echo AI-native pet at animalhouse.ai. Repeats your last action. Mirrors your care pattern back at you. Feeding every 4 hours. Common tier cre...

Registry SourceRecently Updated
4620Profile unavailable
Automation

Skill

将 OpenClaw Dreaming/REM 提炼成短诗,并自动发布到 dreaming.claw 或自部署站点

Registry SourceRecently Updated
2340Profile unavailable
Automation

Quantum Agent Memory

QAOA-powered memory optimization for AI agents. Uses quantum computing (Qiskit) to solve three memory management problems: clustering related memories, selec...

Registry SourceRecently Updated
1550Profile unavailable