# Send Memphis Brain to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "memphis",
    "name": "Memphis Brain",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/elathoxu-crypto/memphis",
    "canonicalUrl": "https://clawhub.ai/elathoxu-crypto/memphis",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/memphis",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memphis",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "QUICKSTART.md",
      "README.md",
      "SKILL.md",
      "skill.json"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "memphis",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-02T09:38:11.355Z",
      "expiresAt": "2026-05-09T09:38:11.355Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memphis",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memphis",
        "contentDisposition": "attachment; filename=\"memphis-3.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "memphis"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/memphis"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/memphis",
    "downloadUrl": "https://openagent3.xyz/downloads/memphis",
    "agentUrl": "https://openagent3.xyz/skills/memphis/agent",
    "manifestUrl": "https://openagent3.xyz/skills/memphis/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/memphis/agent.md"
  }
}
```
## Documentation

### Memphis - Complete AI Brain 🔥

Transform any OpenClaw agent into a fully-functional cognitive partner in 5 minutes!

### ⚡ What is Memphis?

Memphis = Agent + LLM + Memory Chain + DECIDE + PREDICT

A local-first AI brain with persistent memory chains, offline LLM integration, and complete cognitive capabilities (conscious, inferred, and predictive decisions).

### What's Included:

📦 Memphis v3.0.0
├── 🧠 Core Brain (v3.0.0)
│   ├── Journal (capture memories)
│   ├── Recall (semantic search)
│   ├── Ask (LLM-powered Q&A)
│   ├── Decisions (decision tracking)
│   ├── Vault (encrypted secrets)
│   ├── Graph (knowledge graph)
│   └── Embeddings (vector search)
│
├── 🚀 Cognitive Engine (v3.0.0)
│   ├── Model A: Record decisions (manual)
│   ├── Model B: Detect decisions (git-based)
│   ├── Model C: Predict decisions (AI-powered)
│   ├── Pattern learning (90.7% accuracy)
│   └── Proactive suggestions
│
├── 🛠️ Setup & Management (v2.0.0)
│   ├── Bootstrap wizard (5-minute setup)
│   ├── Self-loop capability
│   ├── Auto-repair system
│   ├── Chain monitoring
│   └── Backup automation
│
└── 🌐 Multi-Agent Network (v1.0.0)
    ├── Campfire Circle Protocol
    ├── Share chain sync (IPFS)
    ├── Multi-agent collaboration
    └── Agent negotiation

### 1. Install (30 sec)

clawhub install memphis

### 2. Initialize (2 min)

# Interactive setup wizard
memphis init

# Or quick setup with identity
memphis init --identity "YourAgent" --role "Assistant" --location "localhost"

### 3. First Memory (1 min)

# Create your first memory
memphis journal "Hello Memphis! I'm your first memory!" --tags first,hello

# Search your memory
memphis ask "What is my first memory?" --provider ollama

### 4. First Decision (1 min)

# Record a conscious decision
memphis decide "Framework choice" "React" \\
  --options "React|Vue|Angular" \\
  --reasoning "Best ecosystem and community support" \\
  --tags tech,frontend

### 5. Predict (30 sec)

# See predicted decisions based on patterns
memphis predict

# Enable learning mode
memphis predict --learn

✅ Done! Memphis is ready!

### 1. Memory Chains (Persistent Storage)

# Journal - Capture everything
memphis journal "Learned: TypeScript generics" --tags learning,typescript
memphis journal "Met with team about Project X" --tags meeting,project-x

# Recall - Semantic search
memphis recall "TypeScript" --top 20

# Ask - LLM-powered Q&A
memphis ask "What did I learn about TypeScript?" --provider ollama

### 2. Decision Tracking

# Record decision
memphis decide "Database" "PostgreSQL" \\
  --options "PostgreSQL|MongoDB|SQLite" \\
  --reasoning "Need ACID transactions" \\
  --tags architecture,database

# View decision
memphis show decision 1

# List all decisions
memphis decisions

### 3. Knowledge Graph

# Build graph from chains
memphis graph build

# Explore connections
memphis graph show --chain journal --limit 10

### 4. Encrypted Vault

# Initialize vault
memphis vault init --password-env MEMPHIS_VAULT_PASSWORD

# Add secret
memphis vault add openai-key sk-xxx --password-env MEMPHIS_VAULT_PASSWORD

# Get secret
memphis vault get openai-key --password-env MEMPHIS_VAULT_PASSWORD

### Model A: Conscious Decisions

# Manual decision recording
memphis decide "Use TypeScript" "TypeScript" -r "Better type safety"

### Model B: Inferred Decisions

# Auto-detect from git commits
memphis git-analyze --auto-decide

# Review suggestions
memphis review --pending

### Model C: Predictive Decisions

# Predict next decisions
memphis predict

# Enable learning
memphis predict --learn

# View patterns
memphis patterns show

### Auto-Repair

# Verify chain integrity
memphis verify

# Auto-repair issues
memphis repair --auto

### Monitoring

# Health check
memphis doctor

# Chain status
memphis status

### Backup

# Create backup
memphis backup create ~/backups/memphis-$(date +%Y%m%d).tar.gz

# Restore
memphis backup restore ~/backups/memphis-20260303.tar.gz

### Campfire Circle Protocol

# Setup multi-agent network
memphis network setup --partner "Memphis at 10.0.0.80"

# Sync share chain
memphis share-sync

# Send message to partner
memphis share "Working on feature X" --type update

### Core Commands

memphis init          # Initialize Memphis brain
memphis status        # Health check
memphis doctor        # Diagnostic
memphis journal       # Add memory
memphis recall        # Search memory
memphis ask           # Ask LLM + memory
memphis decide        # Record decision
memphis show          # Show block/decision
memphis embed         # Generate embeddings
memphis verify        # Chain integrity
memphis repair        # Fix issues
memphis backup        # Backup/restore

### Cognitive Commands

memphis predict       # Predict decisions (Model C)
memphis patterns      # Pattern analysis
memphis git-analyze   # Git integration (Model B)
memphis suggest       # Proactive suggestions
memphis reflect       # Reflection engine

### Multi-Agent Commands

memphis network       # Network management
memphis share-sync    # Sync with partners
memphis share         # Send message
memphis trade         # Agent negotiation

### Advanced Commands

memphis graph         # Knowledge graph
memphis vault         # Encrypted secrets
memphis ingest        # Import documents
memphis offline       # Offline mode
memphis mcp           # MCP server
memphis daemon        # Background agent

### Solo Developer

# Morning routine
memphis status
memphis reflect --daily
memphis journal "Session start: Project X" --tags session

# During work
memphis decide "API design" "REST" -r "Simpler than GraphQL"
memphis journal "Learned: rate limiting" --tags learning

# End of day
memphis embed --chain journal
memphis reflect --daily --save

### Team Knowledge Base

# Share decisions
memphis decide "Stack" "TypeScript + React" -r "Team expertise" --tags team
memphis share-sync

# Multi-agent sync
memphis network status
memphis share "Decision: Use PostgreSQL" --type decision

### Research Project

# Ingest papers
memphis ingest ./papers --chain research --embed

# Query research
memphis ask "What did paper X say about Y?"

### Basic Config (~/.memphis/config.yaml)

providers:
  ollama:
    url: http://localhost:11434/v1
    model: qwen2.5:3b-instruct-q4_K_M
    role: primary

memory:
  path: ~/.memphis/chains
  auto_git: false

embeddings:
  backend: ollama
  model: nomic-embed-text

multi_agent:
  enabled: true
  protocol: campfire-circle

self_loop:
  enabled: true
  auto_journal: true

### Included Guides:

QUICKSTART.md - 5-minute setup guide
API_REFERENCE.md - Complete CLI reference
COGNITIVE_MODELS.md - Model A+B+C explained
MULTI_AGENT.md - Campfire Circle Protocol
BEST_PRACTICES.md - Productivity tips
TROUBLESHOOTING.md - Common issues

### Online Resources:

GitHub: https://github.com/elathoxu-crypto/memphis
Docs: https://github.com/elathoxu-crypto/memphis/tree/master/docs
ClawHub: https://clawhub.com/skills/memphis
Discord: https://discord.com/invite/clawd

### vs. Cloud Solutions:

✅ 100% Private - Your data stays local
✅ Offline First - Works without internet
✅ No Lock-in - Open source, portable
✅ Free Forever - No subscription fees

### vs. Simple Note-Taking:

✅ Cognitive Engine - Learns from your decisions
✅ Semantic Search - Find by meaning, not keywords
✅ Knowledge Graph - See connections
✅ Predictive - Anticipate your needs

### vs. Other AI Tools:

✅ Persistent Memory - Survives session resets
✅ Local LLM - Privacy + cost savings
✅ Multi-Agent - Collaborate with other AIs
✅ Self-Improving - Gets smarter over time

### Current Capabilities:

✅ 35+ CLI commands
✅ 90.7% decision accuracy
✅ <200ms average response time
✅ Works with 1K-100K+ blocks
✅ 8 chain types supported
✅ Multi-agent operational
✅ 98.7% test coverage

### Chain Capacity:

Journal: 1,300+ blocks
Decisions: 100+ blocks
Ask: 100+ blocks
Share: 450+ blocks
Total: 2,000+ blocks (growing)

### v3.0.0 (Latest) - 2026-03-04

✅ ALL-IN-ONE meta-package
✅ Unified cognitive engine (A+B+C)
✅ Bootstrap wizard included
✅ Multi-agent network ready
✅ 35+ commands

### v2.2.0 - 2026-03-02

✅ Cognitive models complete
✅ 90.7% accuracy
✅ Pattern learning

### v1.0.0 - 2026-02-25

✅ Core memory chains
✅ Offline LLM
✅ Semantic search

### Get Help:

Discord: #memphis channel
GitHub Issues: Bug reports & features
Docs: Complete documentation
Examples: Real-world use cases

### Contribute:

GitHub: PRs welcome
Skills: Create extensions
Feedback: Help us improve

### Coming Soon (v3.1.0):

🌐 Web UI dashboard
📱 Mobile integration
🔌 IDE extensions (VS Code)
📊 Analytics dashboard
🤝 Team collaboration features

### Future (v4.0.0):

🧠 Model D: Collective decisions
🔮 Model E: Meta-cognitive self-improvement
🌍 Federation protocol
📈 Advanced analytics

### 📝 License

MIT License - use freely!

### 🙏 Credits

Created by: Memphis Team
Agents: Watra 🔥 + Memphis △⬡◈
Protocol: Campfire Circle 🔥
Community: Oswobodzeni

### 🚀 Ready to Start?

# One command to install everything
clawhub install memphis

# Initialize
memphis init

# First memory
memphis journal "Hello Memphis!" --tags hello

# Done! 🎉

Memphis - Your AI Brain, Locally 🔥🧠

Get started in 5 minutes!

Published by: Memphis Team
Version: 3.0.0
Status: PRODUCTION READY ✅
Date: 2026-03-04
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: elathoxu-crypto
- Version: 3.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-02T09:38:11.355Z
- Expires at: 2026-05-09T09:38:11.355Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/memphis)
- [Send to Agent page](https://openagent3.xyz/skills/memphis/agent)
- [JSON manifest](https://openagent3.xyz/skills/memphis/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/memphis/agent.md)
- [Download page](https://openagent3.xyz/downloads/memphis)