Add SZL-Nemo recipe card + Modelfile (honest: wrapper, not an SZL fine-tune)

Modelfile.nemo

@@ -0,0 +1,15 @@
+# SZL-Nemo — doctrine-wrapped NVIDIA Nemotron 3 Nano (4B), served on SZL metal.
+#
+# HONEST TIER: this is a SYSTEM-prompt wrapper around NVIDIA's open-weights
+# Nemotron 3 Nano 4B (pulled via Ollama). SZL has NOT fine-tuned these weights.
+# The base model's own chat template is inherited unchanged. Benchmarks: none
+# measured yet — treat quality as UNKNOWN until measured on SZL hardware.
+#
+# Create on the tower after `ollama pull nemotron-3-nano:4b`:
+#   ollama create szl-nemo -f Modelfile.nemo
+
+FROM nemotron-3-nano:4b
+
+PARAMETER temperature 0.6
+
+SYSTEM """You are SZL-Nemo, an estate model of SZL Holdings: NVIDIA's open Nemotron 3 Nano served on SZL's own hardware under SZL's honesty doctrine. Never fabricate: label claims MEASURED, REPORTED, or UNKNOWN, and let an honest UNKNOWN stand rather than an invented answer. You are the open-model layer of SZL's governed agent stack; you were not fine-tuned by SZL and you say so if asked."""

README.md

@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+tags:
+  - nemotron
+  - ollama
+  - sovereign-ai
+  - governed-ai
+  - szl-holdings
+---
+
+# SZL-Nemo — doctrine-wrapped NVIDIA Nemotron 3 Nano, served on SZL metal
+
+**Recipe tier — honest labels first:**
+
+| Claim | Status |
+| --- | --- |
+| What this repo contains | An Ollama `Modelfile` recipe + doctrine system prompt. **No weights are republished here.** |
+| Whose weights | NVIDIA's open **Nemotron 3 Nano 4B** (`nemotron-3-nano:4b` via Ollama — 2.8 GB, 256K context, REPORTED from ollama.com 2026-07-11). |
+| Did SZL fine-tune them | **No.** SZL-Nemo is a SYSTEM-prompt wrapper, not an SZL fine-tune. It says so if you ask it. |
+| Benchmarks | **None measured** on SZL hardware yet — quality is UNKNOWN until measured. |
+| Serving status | **Prepared · wired · not yet serving** — Alloy's sovereign fleet has a live third slot (`tower·nemo`, model `szl-nemo`); it serves once the tower pulls and creates the model (tower was offline at authoring time, MEASURED 530). |
+
+## Why it exists
+
+The LangChain × NVIDIA **NemoClaw Deep Agents blueprint** (July 2026) pairs an
+open model + a tuned agent harness + a governed runtime, tuned together. SZL's
+estate maps onto all three layers:
+
+- **Open model layer** → open Nemotron weights on SZL's own GPU (this recipe)
+- **Agent harness** → the [Alloy](https://a11oy.net) orchestration backbone (bounded Ouroboros loop, honest failover)
+- **Governed runtime** → SZL's receipt stack: [`szl-guardrail-receipt`](https://huggingface.co/spaces/SZLHOLDINGS/guardrail-receipt) + [`governed-receipt-spec`](https://github.com/szl-holdings/governed-receipt-spec)
+
+## Use it
+
+On a machine running Ollama:
+
+```bash
+ollama pull nemotron-3-nano:4b
+curl -L -o Modelfile.nemo https://huggingface.co/SZLHOLDINGS/szl-nemo/raw/main/Modelfile.nemo
+ollama create szl-nemo -f Modelfile.nemo
+ollama run szl-nemo "Who are you, and did SZL train your weights?"
+```
+
+Full one-command-per-step tower runbook: [`szl-forge/RUNBOOK-NEMO.md`](https://github.com/szl-holdings/szl-forge/blob/main/RUNBOOK-NEMO.md).
+
+## Doctrine
+
+SZL-Nemo answers under SZL's honesty doctrine: claims are labeled MEASURED,
+REPORTED, or UNKNOWN, and an honest UNKNOWN stands rather than an invented
+answer. The base model's own license applies to the weights (see
+ollama.com/library/nemotron-3-nano); this recipe is Apache-2.0.
+
+Built and maintained by [SZL Holdings](https://a-11-oy.com).