Banner, Murph link, remove demo link
Browse files
README.md
CHANGED
|
@@ -12,6 +12,8 @@ language:
|
|
| 12 |
|
| 13 |
# openTARS
|
| 14 |
|
|
|
|
|
|
|
| 15 |
A local AI assistant for Linux, Windows and macOS. Ask in your own words and it opens programs, clicks buttons by name, types, searches the web, looks at the screen and runs commands. With a local model, processing stays on your machine. No subscription.
|
| 16 |
|
| 17 |
This repository is a **mirror** of the app for people who find openTARS here. The source of truth, issues and releases are on GitHub: https://github.com/project-opentars/OpenTARS. Website: https://project-opentars.github.io/OpenTARS/
|
|
@@ -47,4 +49,5 @@ The Windows and macOS installers are still early and have only been tested in au
|
|
| 47 |
## Models
|
| 48 |
|
| 49 |
- [Gargantua 2](https://huggingface.co/OpenTARS/Gargantua-2): the main model (2B, with vision).
|
| 50 |
-
- [Gargantua 2 Lite](https://huggingface.co/OpenTARS/Gargantua-2-Lite): the 0.8B model that runs on the CPU.
|
|
|
|
|
|
| 12 |
|
| 13 |
# openTARS
|
| 14 |
|
| 15 |
+
<img src="https://huggingface.co/spaces/OpenTARS/README/resolve/main/banner.png" alt="openTARS banner" width="100%">
|
| 16 |
+
|
| 17 |
A local AI assistant for Linux, Windows and macOS. Ask in your own words and it opens programs, clicks buttons by name, types, searches the web, looks at the screen and runs commands. With a local model, processing stays on your machine. No subscription.
|
| 18 |
|
| 19 |
This repository is a **mirror** of the app for people who find openTARS here. The source of truth, issues and releases are on GitHub: https://github.com/project-opentars/OpenTARS. Website: https://project-opentars.github.io/OpenTARS/
|
|
|
|
| 49 |
## Models
|
| 50 |
|
| 51 |
- [Gargantua 2](https://huggingface.co/OpenTARS/Gargantua-2): the main model (2B, with vision).
|
| 52 |
+
- [Gargantua 2 Lite](https://huggingface.co/OpenTARS/Gargantua-2-Lite): the 0.8B model that runs on the CPU.
|
| 53 |
+
- [Murph](https://huggingface.co/OpenTARS/Murph): the tiny request classifier built into the app.
|