v1.0.0

GalaxyDesk

GalaxyDesk

Your space to build.

Codex, Google Antigravity, Claude, cloud APIs, and local models.
One native workspace for the things you want to make.

Windows macOS LinuxRust + Tauri

Built in Rust.
Now in your language.

EnglishFrançaisEspañolDeutschУкраїнськаРусский简体中文繁體中文日本語Tagalogहिन्दी
THE BIG PICTURE

Meet the possibilities.

THE WORKSPACE

See the work
take shape.

Work on files. Share a browser view. Inspect changes. Turn a review into Tasks, Bugs, and Features you can follow through a report’s Kanban board.

Planning the build before the first result · Staged public demonstration.
Example project · a report’s Kanban board.
Example project · shared browser preview.
Browse local models, variants and capabilities · Public metadata with demo hardware.
Compare a model’s file, memory estimate and partial profile · Demo hardware; speed not measured.
Import from Codex · Project groups, saved history and linked folders in GalaxyDesk 1.0.0.
Google Antigravity · Connect your installed agy CLI in GalaxyDesk 1.0.0.

Look at the changes.

Readable diffs and guarded file restoration help you inspect what happened.

See the same page.

Browser captures and previews give you and your assistant a shared view.

Keep the review moving.

Stable action references follow the work across models and chats.

Bring your Codex chats.

Open + beside Projects and choose Import from Codex. Search chats by project, keep their history, and link the original folder or choose its new location.

Restore covers captured file changes, not external effects. Parallel workers share project files.

YOUR MODELS

Choose your
kind of brilliant.

A coding engine you already use. A cloud model for the bigger picture. GalaxyDesk Native on your own machine, or another local runtime. Give each conversation the intelligence that fits.

01 / CODING ENGINES

Bring your favourites.

CodexGoogle Antigravity Claude Code Devin CLI · Preview

Use Google Antigravity through your installed agy CLI, alongside Codex and other coding engines. See the account allowances reported by supported CLIs.

Devin CLI is available as a preview.

02 / CLOUD APIS

Open up your options.

OpenAI APIClaude APIGrok APIOllama CloudOpenRouter

Use your provider accounts and the models they make available.

Check configured models and prices automatically, every 30 minutes by default. Completed usage keeps the rates recorded at the time.

03 / LOCAL RUNTIMES

Keep inference close.

GalaxyDesk Native MagnitudeOllamaLM Studio llama.cppvLLM

Open Model Library in the shared workspace pane to browse live GGUF listings, compare hardware and memory estimates, download a verified file and load it natively. You can also connect a separately running local server, including compatible API endpoints.

GalaxyDesk Native is included. External accounts and runtimes are supplied separately. Model capabilities, hardware needs, and provider charges vary.

PROJECT MEMORY

A fresh perspective.
The same project.

You shouldn’t have to start the story again every time you try another model. Keep saved decisions and conversations together, with recalled sources you can look inside.

REMEMBER WHAT MATTERS

Your project’s decisions.

Add, edit, and remove the specifics that guide the work.

KEEP THE ORIGINALS

Your conversation history.

Search saved messages after compaction and return to the source.

CHECK THE CONTEXT

Evidence within reach.

Inspect recalled snippets before building on them.

Memory supports continuity; it does not guarantee a model recalls or interprets every detail correctly.

MULTI-MODEL MODE

A sharp mind.
An extra pair of hands.

Pair a Primary with a Secondary. Give one the lead and the other focused implementation work, then bring the result back for review.

Choose a pairing that fits the task and your budget, including a local worker when your hardware supports it. Delegation and review depend on the models you choose.

PRIMARY

Understand.
Direct. Review.

Focused assignment↓   ↑Result to review
SECONDARY

Build the
next piece.

BUILT IN RUST

Native at the core.
Yours at every turn.

A Rust agent engine and a Tauri desktop form the foundation. Your models, your tools, and your personal touch make it a place to build.

Rust
Native agent engine
Tauri
System web renderer
5
Native builds

Your connections.

Named connections and provider credentials use protected OS-keyring storage.

Your boundaries.

Choose project and chat access. Inspect activity, steer supported engines, and stop managed work.

Your perspective.

See token usage, supported account allowances, and estimates with the model rates recorded at the time.

Room to work separately.

Create native Git worktree chats with isolated folders and branches, shared history, and controls to review or archive the work.

Your desktop companions

Good company. Great character.

Meet Emma, your new assistant, alongside five familiar companions for your desktop.

Emma, Violet, Penelope, Merlin, Clippy and Jeeves are all included. Emma is selected for a new profile; your existing choice stays yours. Choose a companion in Configure → Settings → Pets and turn on Pet Assistant.

Every chat has its place

Live bubbles name the project and conversation. Multiple chats stack, with a checkmark when work finishes. Click a bubble to return to that chat.

A size that suits your desktop

Slide from the original size to twice as big and see the change immediately. Your companion grows; bubble text stays comfortably readable.

Your companion, your choice

Drag your pet into place, switch companions, or turn the overlay off. Custom pet packages remain supported, and your saved choice carries into updates.

YOUR NEXT BIG THING STARTS HERE

Make it yours.

Choose your platform. Connect your intelligence. Open a project.

Choose the installer for your operating system and processor. Connect your own provider account or local model runtime, then open a project and start building. Your saved projects and conversations stay in application data. Already using GalaxyDesk? Update and restart in the app for the latest version.

System requirements and installation help

Memory & storage recommendations

8 GB RAM is recommended for cloud-connected work. Local models need additional RAM or VRAM depending on the model and context size.

Allow around 1 GB for the app, plus free space for updates, projects, attachments, and any local models.

Linux

Use a glibc desktop with WebKitGTK 4.1 and an X11 or Wayland session. AppImage mounting requirements depend on your distribution. If mounting is unavailable, use the extract-and-run option.

The desktop uses WebKitGTK. Shared browser tools use a separately installed compatible browser and its security requirements. Encrypted credentials also need an unlocked desktop keyring.

Your project tools

Install Git, Node.js, Python, compilers, or other dependencies when the project needs them. GalaxyDesk Native is included; other local model servers and coding CLIs are installed separately. Cloud work needs internet and the relevant provider account. Account allowance indicators require a signed-in, supported Codex or Claude Code CLI. Smart auto-complete needs the app open and unlocked.

x64 also means x86_64/AMD64. ARM64 also means AArch64; M-series Macs use ARM64.

Sources: Tauri system dependencies · System web renderers · Local model context and memory.

TAKE IT FURTHER

The details, when you want them.

Explore the connections, controls, and capabilities behind the workspace.

Models & context
Tools & integrations
Built in Rust
Privacy & connection controls
Comparison & fit
Release history