Upload README.md with huggingface_hub

README.md

@@ -18,6 +18,25 @@ viewport.
 **Collection:** Tour Eiffel (Champ-de-Mars diorama), Opéra Garnier,
 Arc de Triomphe, Sacré-Cœur, Moulin Rouge, Panthéon.
 
-Built with [three.js](https://threejs.org) and
-[@mkkellogg/gaussian-splats-3d](https://github.com/mkkellogg/GaussianSplats3D).
-Monument images generated with Ideogram; splats reconstructed with TripoSplat.
+## 🤖 Built agentically via `agents.md`
+
+The whole asset pipeline was produced by an agent calling two Hugging Face
+Spaces through their **`agents.md`** files — machine-readable docs that tell an
+agent exactly how to call a Space's API (endpoints, params, auth, polling). No
+manual clicking: the agent read each `agents.md`, then drove the Spaces end to end.
+
+1. **Images** — [`ideogram-ai/ideogram4`](https://huggingface.co/spaces/ideogram-ai/ideogram4/blob/main/agents.md)
+   generated each monument as a dark-background "specimen" (and the Eiffel as a
+   diorama on a plinth).
+2. **Splats** — [`VAST-AI/TripoSplat`](https://huggingface.co/spaces/VAST-AI/TripoSplat/blob/main/agents.md)
+   reconstructed a 3D Gaussian splat (`.ply`) from each image.
+
+The `.ply` files were then compressed to `.ksplat` (~3× smaller) for fast loading.
+See the `gen_*.py` / `hf_call.py` scripts in this repo — that's the exact pipeline
+the agent ran against those two `agents.md` endpoints.
+
+## Built with
+
+[three.js](https://threejs.org) and
+[@mkkellogg/gaussian-splats-3d](https://github.com/mkkellogg/GaussianSplats3D)
+for rendering.