Full P-Node quickstart - Morpheus Lumerin Node

This page covers a non-TEE provider running on your own infrastructure. For TEE-hardened deployment on SecretVM, see SecretVM quickstart. Hosted alternatives: Docker, AWS EC2, or Akash.

Assumptions

Your AI model is configured, started, and reachable from the proxy-router host on a private endpoint (e.g. http://my-model.example:8080). For testing, a local llama.cpp server with tinyllama works fine — adjust models-config.json if your local port differs.
You have a funded wallet on BASE (MOR + ETH) and the private key for .env.
You have your own ETH node URL — Alchemy or Infura private API key for BASE works (wss://base-mainnet.g.alchemy.com/v2/<key> or HTTPS). The proxy-router has a built-in round-robin of public RPC endpoints as a fallback, but it is rate-limited and unreliable in practice; running a real provider on it leads to silent missed events. Set ETH_NODE_ADDRESS explicitly.
Your proxy-router has a publicly accessible endpoint for the provider (host:port, no protocol), e.g. mycoolmornode.example:3333.

Install & configure

Get the software

Release binary
From source

The proxy-router ships as a standalone binary. Download the latest one for your platform from Releases. Mainnet builds have no suffix; testnet builds end in -test. Asset names look like (version will differ):

Platform	File
Linux (x64)	`linux-x86_64-morpheus-router-<version>`
Linux (ARM64/Raspberry Pi)	`linux-arm64-morpheus-router-<version>`
macOS (Apple Silicon)	`mac-arm64-morpheus-router-<version>`
macOS (Intel)	`mac-x64-morpheus-router-<version>`
Windows (x64)	`win-x64-morpheus-router-<version>.exe`

git clone -b main https://github.com/MorpheusAIs/Morpheus-Lumerin-Node.git
cd Morpheus-Lumerin-Node/proxy-router
./build.sh

Create a working directory

The proxy-router reads its config (.env, models-config.json) and writes its state (./data/, .cookie, proxy.conf) relative to the directory it runs from, so give it a dedicated one and move the binary there (adjust the filename to the version you downloaded):

macOS
Linux
Windows

mkdir -p ~/morpheus-router && cd ~/morpheus-router
mv ~/Downloads/mac-arm64-morpheus-router-* ./proxy-router
chmod 755 proxy-router
xattr -c proxy-router   # clear the quarantine flag (build is not notarized)

mkdir -p ~/morpheus-router && cd ~/morpheus-router
mv ~/Downloads/linux-x86_64-morpheus-router-* ./proxy-router
chmod 755 proxy-router

Create %USERPROFILE%\morpheus-router, move the downloaded win-x64-morpheus-router-<version>.exe into it, and rename it to proxy-router.exe.

Create .env

In the working directory, create a .env file. Start from the repo’s proxy-router/.env.example (.env.example.win on Windows) — the standalone binary does not ship one. Edit at minimum:

WALLET_PRIVATE_KEY= — provider’s private key.
ETH_NODE_ADDRESS= — required for any real deployment. The minimal example file does not set this; without it the node falls back to a built-in public RPC round-robin that is rate-limited and unreliable. Use your own Alchemy / Infura HTTPS or WSS URL. Match ETH_NODE_USE_SUBSCRIPTIONS accordingly (true for WSS, false for HTTPS — recommended HTTPS + false).
Choose mainnet (default) or testnet — uncomment the testnet block, comment mainnet, save.

Full reference: Env: proxy-router (see “Conflicting / overlapping variables” up top).

(Optional) external / pass-through providers

To resell or front another LLM, create models-config.json in the working directory, set MODELS_CONFIG_PATH=./models-config.json in .env, and add the entry:

{
  "modelId": "<your_modelId_from_chain>",
  "modelName": "your-model-name",
  "apiType": "openai",
  "apiUrl": "https://api.example.com/v1/chat/completions",
  "apiKey": "..."
}

Full schema: models-config.json. Restart after edits.

(Optional) provider weights & allowlist

Create rating-config.json in the working directory (and set RATING_CONFIG_PATH=./rating-config.json in .env) to bias selection or restrict to specific providers:

{
  "algorithm": "default",
  "providerAllowlist": [],
  "params": {
    "weights": { "tps": 0.24, "ttft": 0.08, "duration": 0.24, "success": 0.32, "stake": 0.12 }
  }
}

Weights must sum to 1. Reference: rating-config.json.

Start

Run from the working directory (so the relative config and data paths resolve):

macOS / Linux
Windows

cd ~/morpheus-router
./proxy-router

Double-click proxy-router.exe in %USERPROFILE%\morpheus-router. Allow Defender if prompted.

Validate

http://localhost:8082/swagger/index.html should render.
./data/ directory contains logs.

The proxy-router log should include:

INFO  proxy state: running
INFO  HTTP  http server is listening: 0.0.0.0:8082
INFO  TCP   tcp server is listening: 0.0.0.0:3333

Next: register on chain

Once running:

Look up existing models on active.mor.org/status — prefer bidding on an existing modelId.
Register via MyProvider if your admin API is reachable over HTTPS (or use the desktop/local app for HTTP :8082); otherwise use Swagger. Full steps: Register on chain.
Run the self-checks in Verify your provider setup before declaring victory.

Mint a new model only when nothing suitable exists (or you need a new tee-tagged listing).

What can cost you MOR during setup

A few things will quietly draw down your MOR balance during initial configuration. None of them are slashing or forfeiture; they are normal protocol fees and stakes. Knowing them upfront prevents the “I lost ~2 MOR during setup, what happened?” support ticket.

Event	Cost	Refundable?
Register provider (`providerRegister`)	`0.2 MOR` (or `10000 MOR` for subnet)	Yes, on `providerDeregister` (after deregistration cooldown opens)
Register model (`modelRegister`)	`0.1 MOR`	Yes, on `modelDeregister` (model must have no active bids)
Post a bid (`postModelBid`)	`0.3 MOR` non-refundable `marketplaceBidFee`	No — every bid post charges this fee
BASE gas	a few cents in ETH-on-BASE per tx	No (standard gas)
Sessions consumed before your node was actually serving	Possibly small — see “Disputed early closes” in Sessions: stake, close, claim	n/a

The most common pattern: a new provider posts a bid, tweaks their setup, deletes and reposts the bid several times. Each repost charges 0.3 MOR. Six iterations is ~1.8 MOR gone before the node is even serving traffic. Mitigation: finish your model and models-config.json setup, run verify-setup steps 1-4 before posting your first bid. Repost only when pricing actually needs to change. For details on bid pricing and how to change a price, see Pricing.

​Assumptions

​Install & configure

​Start

​Validate

​Next: register on chain