Open Carrusel: AI-Powered Instagram Carousel Builder with Claude

This repository profile is provided by osrepos.com, an open source repository discovery platform.

Open Carrusel: AI-Powered Instagram Carousel Builder with Claude

Summary

Open Carrusel is an open-source, local-first tool for creating Instagram carousels. It leverages AI, specifically Claude, to design pixel-perfect, on-brand slides through natural language chat. Users can export their carousels as PNGs, perfectly sized for Instagram, offering a unique and efficient design workflow.

Repository Information

Analyzed by OSRepos on May 18, 2026

Topics

Click on any tag to explore related repositories

Use at your own risk

OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.

Introduction

Open Carrusel is an innovative, open-source, and local-first tool designed to streamline the creation of Instagram carousels. It empowers creators to generate pixel-perfect, on-brand slides by interacting directly with Claude, an advanced AI model. This project aims to free users from the constraints of expensive closed-source tools or time-consuming manual design processes, offering a unique approach where AI crafts real HTML/CSS slides that are then exported as exact Instagram-dimension PNGs. Everything runs on your local machine, ensuring privacy and control over your data.

Installation

Getting started with Open Carrusel is quick and straightforward, especially with the recommended one-command path.

One-command path (recommended)

  1. Install Claude Code and authenticate.
  2. Clone and open the repo in Claude Code:
    git clone https://github.com/Hainrixz/open-carrusel.git
    cd open-carrusel
    claude
    
  3. In the Claude Code prompt, type:
    /start
    

This command handles dependency installation, starts the dev server, and opens your browser, allowing you to begin designing carousels immediately.

Manual path (if you don't use Claude Code)

git clone https://github.com/Hainrixz/open-carrusel.git
cd open-carrusel
npm run setup        # installs deps + seeds /data/
npm run dev          # starts http://localhost:3000

Note that the AI chat functionality requires Claude Code to be installed, but the editor and export features remain available for static slides.

Examples

Open Carrusel features a highly intuitive three-panel editor designed for an efficient workflow. On the left, you'll find the chat panel where you interact with Claude to generate and refine your slides. The center displays a live preview of your carousel, showing changes in real-time. At the bottom, a drag-reorderable filmstrip allows you to easily manage the sequence of your slides.

You can initiate slide generation with simple prompts, such as "Make me a 5-slide carousel about productivity habits, bold sans-serif, dark mode, accent red." Claude will stream the HTML slides directly into your filmstrip. Iteration is also seamless, allowing you to refine individual slides with commands like "Make slide 3 more minimal" or "Change the accent to teal." The tool supports three Instagram aspect ratios, brand configuration, templates, reference image uploads, and one-click export of pixel-perfect PNGs.

Why Use Open Carrusel?

Open Carrusel offers compelling advantages for content creators:

  • AI-Powered Creativity: Leverage Claude's intelligence to design unique, on-brand, and pixel-perfect slides without wrestling with templates or manual design.
  • Local-First Privacy: All your work, including slides, brand configurations, and uploads, remains on your local machine. No data is sent to external clouds you don't control, ensuring complete privacy and ownership.
  • Open Source Freedom: Released under the MIT license, Open Carrusel provides full transparency and flexibility. Fork it, customize it, or integrate it into your workflow without subscriptions or vendor lock-in.
  • Efficiency and Control: Say goodbye to hours spent on design. Chat-based generation and instant export at exact Instagram dimensions save significant time, allowing you to focus on content.

Links

Related repositories

Similar repositories that may be relevant next.

Colibri: Run 744B GLM-5.2 MoE on Consumer Machines with Pure C

Colibri: Run 744B GLM-5.2 MoE on Consumer Machines with Pure C

July 11, 2026

Colibri is an innovative project that enables running the massive 744B-parameter GLM-5.2 Mixture-of-Experts (MoE) model on consumer-grade machines with as little as 25GB of RAM. It achieves this remarkable feat through a pure C engine with zero dependencies, streaming model experts from disk on demand. This allows users to interact with a frontier-class LLM without requiring expensive GPU hardware.

CLLMAI
Lamini: The Official Python Client for Generative AI API

Lamini: The Official Python Client for Generative AI API

July 6, 2026

Lamini is the official Python client and SDK designed to interact with the Lamini API, enabling developers to create their own Generative AI applications. It provides a straightforward interface for integrating powerful AI capabilities into Python projects. This package simplifies the process of building and deploying generative AI solutions.

PythonAIGenerative AI
RL4LMs: A Modular RL Library for Fine-tuning Language Models

RL4LMs: A Modular RL Library for Fine-tuning Language Models

July 6, 2026

RL4LMs is a powerful and modular reinforcement learning library designed to fine-tune language models to human preferences. It offers easily customizable building blocks for training, including on-policy algorithms, reward functions, and metrics. Thoroughly tested and benchmarked, RL4LMs supports a wide range of NLP tasks and models.

reinforcement-learningnatural-language-processinglanguage-modeling
torchtune: PyTorch Native Library for LLM Post-Training and Experimentation

torchtune: PyTorch Native Library for LLM Post-Training and Experimentation

July 5, 2026

torchtune is a PyTorch native library designed for authoring, post-training, and experimenting with Large Language Models (LLMs). It offers hackable training recipes, simple PyTorch implementations of popular LLMs, and best-in-class memory efficiency. Please note: torchtune is no longer actively maintained as of 2025.

PythonPyTorchLLM

Source repository

Open the original repository on GitHub.

12 counted GitHub visits

View on GitHub
OS
OSRepos

Analysis and discovery of open source repositories. Find interesting projects and follow their updates.

Monitor your website with YourWebsiteScore

OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of third-party repository code is at your own risk. Always review source code, dependencies, licenses, and security implications before running anything.

© 2025 OSRepos. Built with Nuxt 3 and lots of ❤️