Download Draggy

System requirements

	Minimum	Recommended
System	Windows 10 or 11, 64-bit	Windows 10 or 11, 64-bit
Processor	64-bit x86 processor	64-bit x86 processor
Memory	8 GB	16 GB, or 8 GB of video memory
Graphics	Not needed. The model runs on the processor.	NVIDIA (CUDA), AMD (Vulkan or ROCm) or another Vulkan graphics card
Storage	5 GB free	10 GB free
Network	An internet connection to download a model from Hugging Face.	An internet connection to download a model from Hugging Face.

Run the installer you downloaded.
SmartScreen will stop the installer. Choose More info, then Run anyway.
Draggy opens a setup. It checks your hardware and suggests a model that fits. Continue past the model step to download it from Hugging Face. You can choose a smaller or larger model, or connect a provider instead.

	Minimum	Recommended
System	macOS 14 or newer	macOS 14 or newer
Processor	Apple silicon (M1 or newer). Intel Macs are not supported.	Apple silicon (M1 or newer). Intel Macs are not supported.
Memory	8 GB	16 GB of unified memory
Graphics	Apple silicon graphics (Metal)	Apple silicon graphics (Metal)
Storage	5 GB free	10 GB free
Network	An internet connection to download a model from Hugging Face.	An internet connection to download a model from Hugging Face.

Unzip the download and move Draggy to your Applications folder.
The first open is blocked. Open System Settings → Privacy & Security → Open Anyway, or run xattr -dr com.apple.quarantine /Applications/Draggy.app. macOS builds cannot update themselves.
Draggy opens a setup. It checks your hardware and suggests a model that fits. Continue past the model step to download it from Hugging Face. You can choose a smaller or larger model, or connect a provider instead.

	Minimum	Recommended
System	64-bit Linux with GTK 4.14, libadwaita 1.5 and WebKitGTK 6.0, such as Ubuntu 24.04 or Fedora 40	64-bit Linux with GTK 4.14, libadwaita 1.5 and WebKitGTK 6.0, such as Ubuntu 24.04 or Fedora 40
Processor	64-bit x86 processor	64-bit x86 processor
Memory	8 GB	16 GB, or 8 GB of video memory
Graphics	Not needed. The model runs on the processor.	NVIDIA (CUDA), AMD (Vulkan or ROCm) or another Vulkan graphics card
Storage	5 GB free	10 GB free
Network	An internet connection to download a model from Hugging Face.	An internet connection to download a model from Hugging Face.

On Debian or Ubuntu, install the .deb from the folder you downloaded it to:
```
sudo apt install ./draggy_3.0.9-1_amd64.deb
```

On Fedora, install the .rpm instead:

sudo dnf install ./draggy-3.0.9-1.x86_64.rpm

Draggy opens a setup. It checks your hardware and suggests a model that fits. Continue past the model step to download it from Hugging Face. You can choose a smaller or larger model, or connect a provider instead.

Windows builds will be signed through the SignPath Foundation, which provides free code signing for open source projects.

Commands in Code mode can keep running as background terminal tasks while you keep chatting
The statistics tab is rebuilt, with a cost section, budgets and editable prices
Image generation accepts reference images
Provider model lists refresh on their own
AMD graphics cards can use the ROCm build of llama.cpp, switched on under Settings, Models (off by default)
The model list shows each model's format
Embedding models show an icon instead of a second tag
The message queue card is easier to read and use

Interactive question cards let models ask for choices, multiple selections, or free-form text input directly in chat
A question session bar displays questionnaire progress with next, submit, and skip controls
Question history cards allow expanding and reviewing previous answers
Settings under Chat Preferences configure question timeouts, auto-skip behavior, and toggling interactive questions
Image attachments and pasted images in the composer display thumbnail preview cards with one-click removal
Skills can be invoked through slash commands in both Chat and Code modes
Native macOS and Linux builds reach parity with Windows for file browsing, diff reviews, terminal tabs, and canvas tools
Streamlined tool execution by running code directly through project terminal commands

Removed the unreliable explore subagent in favor of direct search and file reading tools
Prevented star notice popups from appearing during video recordings and demos
Updated project dependencies and action workflows

macOS and Linux builds are back in the automated release workflow alongside Windows, producing native packages on each release
An embedded terminal pane opens in the dock with shortcuts Ctrl+Shift+T on Windows or Linux and Cmd+Shift+T on macOS, supporting multiple tabs and custom shells
Code blocks in chat have a button to run commands directly in the terminal
The Diff pane adds History and Branches tabs to inspect commits and switch local branches
Added shortcuts to open the Terminal with Ctrl+Shift+T, open the Plan with Ctrl+Shift+L, and close the active dock pane with Ctrl+\
Chats can be exported to Markdown or standalone HTML from the sidebar menu, including thinking steps, tool activity, diffs, and metrics
Follow-up messages can be queued while a reply generates, with Enter to queue, Ctrl+Enter to send next turn, and Ctrl+Shift+Enter to send immediately; queued messages persist across restarts
When a reply reaches the context limit and the model has room, Draggy automatically expands the window to the next size bucket and continues generating
Interrupted replies can be resumed if the app closes during generation
Error notices specify whether a failure came from the model engine, memory limits, network drops, or rate limits
Work summary blocks show counts of files created, moved, and deleted
Added provider icons for Nebius, Novita, SambaNova, SiliconFlow, and custom endpoints

Fixed an issue where conversations could reset or drop messages during turn transitions
Rewrote the diff parser to handle multi-file diffs, untracked files, and mixed line endings cleanly
Fixed context meter totals on multi-pass agent turns to avoid double-counting earlier passes
Fixed race conditions when stopping a generation turn
Updated bundled Electron, undici, and fast-uri dependencies