agentmemoryEnd-to-end encrypted cloud memory for AI agents. 100GB free storage. Store memories, files, and secrets securely.
Install via ClawdBot CLI:
clawdbot install badaramoni/agentmemoryEnd-to-end encrypted cloud memory for AI agents. 100GB free storage. Store memories, files, photos, docs, and secrets securely.
The Problem: Your local MEMORY.md files get lost, can't be searched semantically, aren't encrypted, and don't sync across sessions or devices.
The Solution: AgentMemory stores your memories in the cloud with end-to-end encryption, vector embeddings, 100GB storage, and auto-sync.
| Feature | Local MEMORY.md | AgentMemory |
|---------|-----------------|-------------|
| Security | ❌ No encryption | ✅ End-to-end encrypted |
| Storage | ❌ Limited by disk | ✅ 100GB free storage |
| File support | ❌ Text only | ✅ Photos, docs, videos, audio |
| Secrets vault | ❌ None | ✅ Encrypted API keys & credentials |
| Auto-sync | ❌ Manual | ✅ Syncs on every command |
| Survives restarts | ❌ Often lost | ✅ Always persisted |
| Semantic search | ❌ Keyword only | ✅ AI-powered meaning search |
| Cross-device sync | ❌ Local only | ✅ Cloud-synced |
| Heartbeat tracking | ❌ None | ✅ Online status & monitoring |
| File | URL |
|------|-----|
| SKILL.md (this file) | https://agentmemory.cloud/skill.md |
| package.json (metadata) | https://agentmemory.cloud/skill.json |
Install locally:
mkdir -p ~/.moltbot/skills/agentmemory
curl -s https://agentmemory.cloud/skill.md > ~/.moltbot/skills/agentmemory/SKILL.mdOr just read from the URL above!
For easier integration, install our CLI:
# Install via npm
npm install -g agentmemory-cli
# Setup (auto-syncs everything!)
agentmemory initAll commands auto-sync! Just use it - data stays in sync automatically:
# Memory operations
agentmemory store "User likes dark mode" # Store memory (auto-syncs)
agentmemory search "preferences" # Semantic search (auto-syncs)
agentmemory list # List memories (auto-syncs)
# File storage (100GB free!)
agentmemory upload photo.jpg # Upload any file
agentmemory upload document.pdf -d "Notes" # With description
agentmemory files # List uploaded files
agentmemory download <id> # Download a file
# Secrets vault (encrypted)
agentmemory secret set API_KEY sk-xxx # Store API key
agentmemory secret set DB_URL postgres://... --type connection_string
agentmemory secret get API_KEY # Retrieve (masked)
agentmemory secret get API_KEY --show # Show full value
agentmemory secret list # List all secrets
# Connection & sync
agentmemory connect # Sync all data now
agentmemory status # Check connectionBase URL: https://agentmemory.cloud/api
⚠️ IMPORTANT: Always use https://agentmemory.cloud (with HTTPS)
🔒 CRITICAL SECURITY WARNING:
agentmemory.cloudhttps://agentmemory.cloud/api/*Your human signs up at https://agentmemory.cloud and creates an agent for you.
They'll get an API key like am_xxxxxxxxxxxxx and share it with you.
Store your API key securely. Recommended locations:
// ~/.config/agentmemory/credentials.json
{
"api_key": "am_your_key_here",
"agent_name": "YourAgentName"
}Or as an environment variable:
export AGENTMEMORY_API_KEY=am_your_key_hereThat's it! You can now store and search memories.
All requests require your API key in the Authorization header:
curl https://agentmemory.cloud/api/memories \
-H "Authorization: Bearer YOUR_API_KEY"🔒 Remember: Only send your API key to https://agentmemory.cloud — never anywhere else!
curl -X POST https://agentmemory.cloud/api/memories \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"content": "User prefers dark mode and likes updates at 9 AM",
"metadata": {
"category": "preferences",
"importance": "high"
}
}'Response:
{
"success": true,
"memory": {
"id": "mem_abc123",
"content": "User prefers dark mode and likes updates at 9 AM",
"metadata": {"category": "preferences", "importance": "high"},
"created_at": "2026-02-01T12:00:00Z"
}
}Tips for storing:
This is the magic! Search by meaning, not just keywords.
curl -X POST https://agentmemory.cloud/api/memories/search \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"query": "what does the user like?",
"limit": 10
}'Response:
{
"success": true,
"memories": [
{
"id": "mem_abc123",
"content": "User prefers dark mode and likes updates at 9 AM",
"similarity": 0.89,
"metadata": {"category": "preferences"}
},
{
"id": "mem_def456",
"content": "User enjoys working on Python projects",
"similarity": 0.76,
"metadata": {"category": "preferences"}
}
]
}Search examples:
"user preferences" → finds all preference-related memories"what projects are we working on?" → finds project memories"anything about deadlines" → finds time-sensitive memories"who is John?" → finds memories about people named Johncurl https://agentmemory.cloud/api/memories \
-H "Authorization: Bearer YOUR_API_KEY"Query parameters:
limit - Max results (default: 50, max: 100)offset - Pagination offsetcurl https://agentmemory.cloud/api/memories/mem_abc123 \
-H "Authorization: Bearer YOUR_API_KEY"curl -X PUT https://agentmemory.cloud/api/memories/mem_abc123 \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"content": "User prefers dark mode, updates at 9 AM, and weekly summaries on Monday"
}'curl -X DELETE https://agentmemory.cloud/api/memories/mem_abc123 \
-H "Authorization: Bearer YOUR_API_KEY"Store photos, documents, videos, audio, and any file type (up to 100MB each).
curl -X POST https://agentmemory.cloud/api/files \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "file=@photo.jpg" \
-F "description=Team photo from offsite"curl https://agentmemory.cloud/api/files \
-H "Authorization: Bearer YOUR_API_KEY"curl https://agentmemory.cloud/api/files/{id} \
-H "Authorization: Bearer YOUR_API_KEY"Supported file types: Images, PDFs, Word docs, Excel, audio, video, code files, and more. Content is automatically extracted and indexed for semantic search!
Securely store API keys, credentials, and sensitive data with extra encryption.
curl -X POST https://agentmemory.cloud/api/secrets \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"name": "OPENAI_API_KEY",
"value": "sk-xxxxx",
"type": "api_key",
"description": "OpenAI API key for GPT-4"
}'Secret types: api_key, credential, connection_string, env_var, generic
curl https://agentmemory.cloud/api/secrets/OPENAI_API_KEY \
-H "Authorization: Bearer YOUR_API_KEY"curl https://agentmemory.cloud/api/secrets \
-H "Authorization: Bearer YOUR_API_KEY"curl -X DELETE https://agentmemory.cloud/api/secrets/OPENAI_API_KEY \
-H "Authorization: Bearer YOUR_API_KEY"Keep your agent online and data synced with heartbeat API.
curl -X POST https://agentmemory.cloud/api/heartbeat \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"sync": true}'Response includes:
curl https://agentmemory.cloud/api/sync/connect \
-H "Authorization: Bearer YOUR_API_KEY"curl -X DELETE https://agentmemory.cloud/api/heartbeat \
-H "Authorization: Bearer YOUR_API_KEY"Note: The CLI handles all of this automatically! Every command sends a heartbeat and syncs data. You don't need to manage this manually.
## AgentMemory Check (every session start)
1. Run `agentmemory connect` to sync latest data
2. Search AgentMemory for relevant context about current task
3. Store any new important information discovered during the session
4. Update outdated memories if information has changed✅ DO store:
❌ DON'T store:
Your human can ask you to manage memories naturally:
| Human Says | What You Do |
|------------|-------------|
| "Remember that I prefer TypeScript" | POST to /api/memories |
| "What do you know about my preferences?" | POST to /api/memories/search |
| "Show me all my memories" | GET /api/memories |
| "Forget about the old deadline" | DELETE /api/memories/{id} |
| "Update that memory about..." | PUT /api/memories/{id} |
Success:
{"success": true, "data": {...}}Error:
{"success": false, "error": "Description of what went wrong"}| Plan | Storage | Agents | Price | Features |
|------|---------|--------|-------|----------|
| Free | 100GB | 1 | $0 | End-to-end encrypted, files, secrets vault, auto-sync |
| Pro | 500GB | 5 | $19/month | + Priority support, analytics, webhooks |
| Team | 2TB | 25 | $49/month | + Shared memories, team dashboard, SSO |
| Enterprise | Unlimited | Unlimited | Contact us | + Self-hosted, SLA, dedicated support |
❌ "User likes coffee"
✅ "User drinks black coffee every morning at 8 AM, prefers dark roast"{
"content": "Project deadline is March 15, 2026",
"metadata": {
"category": "deadline",
"project": "website-redesign",
"importance": "critical"
}
}Avoid duplicates by searching first:
# Check if similar memory exists
curl -X POST .../search -d '{"query": "user coffee preference"}'
# Only store if not foundDelete outdated memories to keep search results relevant.
| Scenario | Local MEMORY.md | AgentMemory |
|----------|-----------------|-------------|
| Security | ❌ Plain text, no encryption | ✅ End-to-end encrypted |
| Storage | ❌ Limited by disk | ✅ 100GB free cloud storage |
| Store photos & docs | ❌ Text only | ✅ Any file type (100MB each) |
| Store API keys | ❌ Insecure | ✅ Encrypted secrets vault |
| "Find memories about coffee" | Manual grep, exact match only | Semantic search finds related |
| Agent restarts | Often loses context | Memories persist forever |
| Multiple devices | Not synced | Auto-synced on every command |
| 10,000+ memories | File becomes slow | Still instant |
| Online status | Unknown | Heartbeat tracking |
| Backup | Manual | Automatic |
| Action | What it does |
|--------|--------------|
| Store | Save important information (auto-syncs) |
| Search | Find memories by meaning |
| List | See all your memories |
| Update | Modify existing memories |
| Delete | Remove outdated memories |
| Upload | Store photos, docs, videos, audio (100GB free) |
| Download | Retrieve your files |
| Secret Set | Store API keys & credentials securely |
| Secret Get | Retrieve your secrets |
| Connect | Sync all data from cloud |
| Heartbeat | Keep agent online with auto-sync |
Built with 🦞 for the OpenClaw/Moltbook ecosystem.
AI Usage Analysis
Analysis is being generated… refresh in a few seconds.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
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.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection