Add organization card

README.md

@@ -1,10 +1,28 @@
 ---
-title: README
-emoji: 🦀
-colorFrom: yellow
-colorTo: red
+title: openTARS
+emoji: 🤖
+colorFrom: indigo
+colorTo: gray
 sdk: static
-pinned: false
+pinned: true
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# openTARS
+
+**A local AI assistant for your computer.** It runs on your own machine, with no account and no cloud by default. It opens programs, types, clicks, searches the web, runs commands, reads your files, and can look at a screenshot.
+
+- **Gargantua 2**: the main model, Qwen3.5 2B fine-tuned for the assistant, with vision. [Model card](https://huggingface.co/ProjectOpenTARS/Gargantua-2)
+- **Gargantua 2 Lite**: a 0.8B model that runs on the CPU, for machines without a graphics card. [Model card](https://huggingface.co/ProjectOpenTARS/Gargantua-2-Lite)
+
+Both models are also on Ollama as `ProjectOpenTARS/Gargantua-2`.
+
+## Links
+
+- Website and downloads: https://project-opentars.github.io/OpenTARS/
+- Source code (MIT): https://github.com/project-opentars/OpenTARS
+- Contact: projectopentars@gmail.com
+
+## Licenses
+
+- The openTARS code is MIT.
+- The Gargantua models are Apache-2.0, based on Qwen3.5 (Apache-2.0). Each model card has the measured results and the known limits.