back to top
HomeSoftwareOpen CoDesign: Open Source AI Design Tool to Turn Prompts into UI,...

Open CoDesign: Open Source AI Design Tool to Turn Prompts into UI, Prototypes & Slides

Open source alternative to Claude Design, with support for GPT, Gemini, and other models.

- Advertisement -

File Info

FileDetails
NameOpen CoDesign
Versionv0.1.4
TypeAI Design + Prototype Tool
DeveloperOpenCoworkAI
LicenseMIT (Open Source)
PlatformsWindows • macOS • Linux
File Formats.exe • .dmg • .AppImage • .deb • .rpm
Primary UseTurn prompts into UI designs, prototypes, slides, and assets
GitHub RepositoryGithub/open-codesign

Description

Open CoDesign is weird in a good way. You write a prompt. Something shows up next to it. Actual stuff you can use or export.

It runs on your laptop. You plug in whatever model you already use, Claude, GPT, Gemini, even Ollama. You can see the agent working, pause it, or just fix one small part instead of starting over. That sounds minor, but it changes how you use it.

It’s not perfect. Some outputs miss. Some feel rough. But when it clicks, you go from blank prompt to something usable in minutes. Probably the easiest way to think about it is a design tool that behaves like a coding companion. Just speeds up the part where you turn an idea into something real.

Use Cases

  • Generate landing pages from a prompt
  • Create pitch decks or slides quickly
  • Build UI prototypes without opening Figma
  • Turn ideas into working HTML/React layouts
  • Iterate on designs by clicking and editing parts
  • Export designs as real usable files

Screenshots

Features of Open CoDesign

FeatureDescription
Prompt to DesignGenerate full UI from a single prompt
Live PreviewSee the design update in real time
Click-to-EditEdit specific sections without regenerating everything
Multi-Model SupportWorks with OpenAI, Claude, Gemini, Ollama, etc.
Local AppRuns on your desktop, not browser-only
Export OptionsHTML, PDF, PPTX, ZIP, Markdown
Design HistorySaves previous versions locally
Responsive PreviewSwitch between mobile, tablet, desktop views
AI Tweaks PanelAdjust colors, spacing, typography easily
Offline ControlYour app runs locally (model calls depend on provider)
Related: OpenPencil (Design-as-Code): AI-Native UI Editor with Prompt-to-UI & Code Generation

System Requirements

ComponentRequirement
Operating SystemWindows 10+, macOS 12+, Linux
ProcessorAny modern CPU
RAM4 GB minimum (8 GB recommended)
DependenciesAPI key (or local Ollama)
Related: Open Source Developer Tools Worth Switching to

How to Install Open CoDesign?

Windows

  1. Download the .exe file
  2. Double-click to start installation
  3. Open the app after install

macOS

  1. Download the .dmg file
  2. Open it and drag the app to Applications
  3. Launch the app

Linux

AppImage

  1. Download .AppImage
  2. Right-click -> Properties -> allow execution
  3. Double-click to run

.deb (Ubuntu/Debian)

  1. Download .deb
  2. Double-click -> install via package manager

.rpm (Fedora/RHEL)

  1. Download .rpm
  2. Open with Software Installer and install

Download Open CoDesign AI Design Tool

An open source alternative to Claude Design

Open CoDesign is the kind of thing you open once and then keep coming back to.

You type an idea, it builds something. Then you fix parts of it like a normal design tool instead of rewriting the whole prompt again and again. It’s not replacing Figma. Some outputs still miss. But for quick ideas or first drafts, it cuts a lot of the boring setup.

The control is the nice part. You’re not locked into one model. Use whatever API you already have and switch if you feel like it.

Don’t miss any Tech Story

Subscribe To Firethering NewsLetter

You Can Unsubscribe Anytime! Read more in our privacy policy

LEAVE A REPLY

Please enter your comment!
Please enter your name here

YOU MAY ALSO LIKE
Amuse Easily Run AI Image, Video, Audio & Text Models Locally on Windows

Amuse: Easily Run AI Image, Video, Audio & Text Models Locally on Windows

0
Running AI models locally usually means dealing with Python environments, dependency conflicts, model downloads, and complex tools like ComfyUI. Amuse got you covered if you don't want any hurdle of spending hours configuring workflows, you install the app, pick a model, and start generating. The software automatically handles its own isolated Python environment while providing a clean desktop interface for image generation, video creation, speech recognition, voice synthesis, upscaling, interpolation, and AI-powered editing. It acts more like a local AI studio, bringing together popular image, video, audio, and text models under one interface.
Sefirah Open-Source Android & Windows Sync App for Clipboard, Files, Notifications, and Screen Mirroring

Sefirah: Open-Source Android & Windows Sync App

0
If you've ever wished your Android phone and Windows PC behaved like parts of the same device, Sefirah is trying to solve exactly that. Instead of focusing on cloud syncing or complicated account setups, it creates a direct connection between your phone and computer so everyday tasks feel faster. Copy something on your phone and paste it on your PC. Send files between devices. Mirror your Android screen. Read notifications on your desktop. Even control media playback remotely. Features that normally require multiple apps are available inside a single tool, while everything stays on your local network.
DeepSeek GUI Desktop App

DeepSeek GUI: Local AI Coding Assistant, Agent Workbench & DeepSeek Desktop App

0
DeepSeek has become one of the most popular AI models for coding and technical work, but using it often means juggling browser tabs, API keys, terminals, and separate tools. DeepSeek GUI is made to solve this problem. Instead of treating DeepSeek like a chatbot in a browser, it turns it into a desktop workspace. You can work on code, write documents, create implementation plans, review changes, manage long-running goals, and even run background tasks without bouncing between half a dozen applications. Under the hood is Kun, a local runtime designed to keep agent sessions organized and make better use of context. It focuses on reducing wasted tokens, reusing cached prompts, and exposing tools only when they're actually needed. The result feels like having a dedicated workspace built around DeepSeek. Projects, plans, reviews, writing, and automation all stay connected.