⚠️ Morpheus Skill is experimental beta open source software for testers only. Use at your own risk.

Morpheus Skill

v2026.4.18

Open-source first. GLM-5 handles everything — Claude is the escape hatch, not the default. AI inference you own, via the Morpheus decentralized network.

Formerly EverClaw

Get Started

Choose your starting point:

🆕

New to OpenClaw

One command installs everything — OpenClaw, Morpheus Skill, and all dependencies

Already have OpenClaw

Add Morpheus Skill to your existing setup

One-Line Install

1

Install Everything

One command. Zero prompts. Detects your OS and hardware, installs all dependencies (Node.js, OpenClaw, Morpheus Skill), and configures your agent automatically:

curl -fsSL https://get.everclaw.xyz | bash

This guided installer:

  • ✅ Checks for required dependencies (curl, git, Node.js, npm, Homebrew, OpenClaw)
  • ✅ Auto-installs missing dependencies with real verification
  • ✅ Works on admin and non-admin macOS accounts (nvm fallback for Node.js)
  • ✅ Supports Apple Silicon and Intel Macs, Linux x86_64 and arm64
  • ✅ Bootstraps a free GLM-5 starter key (1,000 requests/day)
  • ✅ Optionally installs the Morpheus proxy-router for P2P inference
2

Configure Your Agent

The installer runs setup automatically, but if you need to reconfigure later:

node ~/.openclaw/workspace/skills/everclaw/scripts/setup.mjs --key YOUR_KEY --apply --test --restart

Get a free API key at app.mor.org. Gateway-only (no local proxy): add --template gateway-only.

Optional: For local P2P inference (stake MOR tokens), continue with steps 3–5:

3

Create Your Wallet

Generates an Ethereum wallet and stores the private key in your macOS Keychain. No external accounts needed.

node ~/.openclaw/workspace/skills/everclaw/scripts/everclaw-wallet.mjs setup
4

Fund Your Wallet

Send ETH to your wallet address (shown after setup). You need a small amount of ETH on Base for gas and to swap for MOR tokens:

# Swap 0.05 ETH for MOR tokens node ~/.openclaw/workspace/skills/everclaw/scripts/everclaw-wallet.mjs swap eth 0.05 # Approve MOR for staking node ~/.openclaw/workspace/skills/everclaw/scripts/everclaw-wallet.mjs approve
5

Start Inference

Launch the Morpheus router. Your agent now has access to decentralized AI inference.

bash ~/.openclaw/workspace/skills/everclaw/scripts/start.sh

💡 MOR is staked, not spent

When you open an inference session, your MOR tokens are locked as a deposit. When the session ends, they come back. Stake them again for a new session. This is what makes the access yours forever — you're not buying consumable API credits.

Add Morpheus Skill to OpenClaw

1

Install Morpheus Skill

Install from ClawHub or the command-line installer:

clawhub install everclaw-inference

Or use the full installer: curl -fsSL https://get.everclaw.xyz | bash

2

Configure Your Agent (setup.mjs)

One command configures Morpheus providers in your OpenClaw config. Get a free API key at app.mor.org, then:

node ~/.openclaw/workspace/skills/everclaw/scripts/setup.mjs --key YOUR_KEY --apply --test --restart

Gateway-only (no local proxy): add --template gateway-only. Dry-run first (omit --apply) to preview changes.

Optional: For local P2P inference (stake MOR tokens), continue with steps 3–6:

3

Install Router, Proxy & Guardian

Two commands set up the Morpheus router, OpenAI-compatible proxy, and gateway health monitor:

bash ~/.openclaw/workspace/skills/everclaw/scripts/install.sh bash ~/.openclaw/workspace/skills/everclaw/scripts/install-proxy.sh
4

Create Your Wallet

Generates a wallet and stores the key in macOS Keychain. No 1Password, no external accounts.

node ~/.openclaw/workspace/skills/everclaw/scripts/everclaw-wallet.mjs setup
5

Fund & Swap

Send ETH (on Base) to your wallet address, then swap for MOR:

# Swap ETH for MOR node ~/.openclaw/workspace/skills/everclaw/scripts/everclaw-wallet.mjs swap eth 0.05 # Approve MOR for staking node ~/.openclaw/workspace/skills/everclaw/scripts/everclaw-wallet.mjs approve
6

Start Inference

Launch the Morpheus router:

bash ~/.openclaw/workspace/skills/everclaw/scripts/start.sh

💡 MOR is staked, not spent

When you open an inference session, your MOR tokens are locked as a deposit. When the session ends, they come back. Stake them again for a new session. This is what makes the access yours forever — you're not buying consumable API credits.

How It Works

Stake MOR tokens for inference sessions. When the session ends, your MOR comes back. Stake again. Forever.

Your Agent
Morpheus Skill Proxy
Morpheus P2P
AI Model

What's Included

🚀

One-Line Install

One command installs everything — OpenClaw, Morpheus Skill, Node.js, dependencies. Zero prompts, auto-detects your hardware.

🔑

Free Starter Key

Bootstrap with a free GLM-5 key (1,000 requests/day) via the Morpheus API Gateway. No wallet needed to get started.

♾️

Decentralized Inference

Access GLM-5, GLM-5.1, GLM-4.7 Flash, Kimi K2.5, and 30+ models through the Morpheus P2P network.

🔌

OpenAI-Compatible Proxy

Standard API format. Auto-opens 7-day sessions, renews before expiry, auto-retries on session errors, and returns cooldown-safe error codes.

🧭

Open-Source First Router

13-dimension classifier, <1ms. Routes trivial tasks to GLM Flash, everything else to GLM-5 — all on Morpheus. Claude is fallback only.

💸

x402 Payments

Pay any x402-enabled agent with USDC on Base. Automatic 402 detection, EIP-712 signing, budget controls, and dry-run mode.

📋

ERC-8004 Registry

Discover agents on-chain. Read identity, services, endpoints, and reputation from the Base mainnet registries.

🛡️

Gateway Guardian v5

Billing-aware escalation — classifies errors, skips useless restarts for credit exhaustion. Direct curl inference probes, credit monitoring, circuit breaker, nuclear self-healing restart.

🔐

Zero-Dependency Wallet

Private keys stored in macOS Keychain. No 1Password, no external accounts. Generate, swap, and stake in one script.

🧠

Local Ollama Fallback

Hardware-aware model selection — Gemma 4 family (E2B/E4B/26B/31B) with vision + audio, auto-selected based on available RAM/GPU.

🔍

SkillGuard Scanner

Scan skills for malicious patterns before installing. Protects against supply chain attacks.

🧱

Prompt Injection Defense

Multi-language detection, severity scoring, and HiveFence threat intelligence network.

Available Models

Model Type Notes
GLM-5 ⭐GeneralDefault — Opus 4.5-level, STANDARD + HEAVY tier
GLM-5.1GeneralLatest GLM model
GLM 4.7 FlashFastLIGHT tier — cron, heartbeats, simple lookups
Kimi K2.5GeneralSolid general model
Kimi K2 ThinkingReasoningExtended thinking for complex tasks
GLM-5:webGeneral + WebGLM-5 with web search
GLM-5.1:webGeneral + WebGLM-5.1 with web search
Qwen3 235BGeneralLarge parameter count
GPT-OSS 120BGeneralOpenAI's open-source model