{"id":14964499,"url":"https://github.com/bigsk1/ai-screen-analyzer","last_synced_at":"2025-08-03T01:32:24.794Z","repository":{"id":249782864,"uuid":"832536378","full_name":"bigsk1/ai-screen-analyzer","owner":"bigsk1","description":"AI Screen Analyzer allows users to capture screenshots, analyze them using various AI providers and models, and engage in conversations about the images.","archived":false,"fork":false,"pushed_at":"2024-10-29T00:20:59.000Z","size":2294,"stargazers_count":8,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-12-05T07:02:36.063Z","etag":null,"topics":["ai-chatbot-framework","ai-image-recognition","ai-vision","anthropic-claude","claude","gpt-4o-mini","gpt4o","homelab","image-recognition","llama","llama3-1","mistral","ollama","openai","self-hosted"],"latest_commit_sha":null,"homepage":"https://bigsk1.com","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bigsk1.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null},"funding":{"github":"bigsk1"}},"created_at":"2024-07-23T08:14:03.000Z","updated_at":"2024-11-30T23:14:33.000Z","dependencies_parsed_at":"2024-09-13T22:40:54.198Z","dependency_job_id":"a442d380-53ce-4794-be24-41f59f8c4cc3","html_url":"https://github.com/bigsk1/ai-screen-analyzer","commit_stats":{"total_commits":19,"total_committers":2,"mean_commits":9.5,"dds":0.3157894736842105,"last_synced_commit":"506fba015c384712d3ce21d74a657f00cca12eb9"},"previous_names":["bigsk1/ai-screen-analyzer"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigsk1%2Fai-screen-analyzer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigsk1%2Fai-screen-analyzer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigsk1%2Fai-screen-analyzer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigsk1%2Fai-screen-analyzer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bigsk1","download_url":"https://codeload.github.com/bigsk1/ai-screen-analyzer/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":228268483,"owners_count":17893985,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-chatbot-framework","ai-image-recognition","ai-vision","anthropic-claude","claude","gpt-4o-mini","gpt4o","homelab","image-recognition","llama","llama3-1","mistral","ollama","openai","self-hosted"],"created_at":"2024-09-24T13:33:16.277Z","updated_at":"2025-08-03T01:32:24.778Z","avatar_url":"https://github.com/bigsk1.png","language":"JavaScript","funding_links":["https://github.com/sponsors/bigsk1"],"categories":[],"sub_categories":[],"readme":"# AI Screen Analyzer\n\nAI Screen Analyzer is a powerful web application that allows users to capture screenshots, analyze them using various AI providers and models, and engage in conversations about the captured images.\n\n![Image](https://github.com/user-attachments/assets/997bd717-6f7f-4c83-b0aa-395360ea4698)\n\n## 🚀 Features\n\n- **Modern UI**: Sleek, responsive interface with dark/light mode and glass morphism effects\n- **Screen Capture**: Easily capture screenshots of your desktop or specific windows\n- **Multi-Model AI Analysis**: Analyze images using multiple AI models:\n  - OpenAI's GPT-4o Vision\n  - Anthropic's Claude 3 \n  - Ollama's local models (including LLaVA)\n- **Intelligent Chat**: Engage in conversations about the analyzed images or any topic\n- **Model Switching**: Seamlessly switch between different AI models without losing context\n- **Dark/Light Mode**: Toggle between dark and light themes based on preference or system settings\n- **Capture History**: View and manage your recent screen captures\n- **Responsive Design**: Works great on desktop and mobile devices\n- **Local Setup**: Run the application locally for enhanced privacy and customization\n- **Docker Support**: Run in Docker for easy deployment\n\n\n## ✨ Use Cases\n\n- **UI/UX Research**: Capture and analyze interfaces for design inspiration\n- **Code Generation**: Capture a website you like and ask the AI to provide the code\n- **Technical Support**: Take screenshots of errors and get AI assistance\n- **Content Analysis**: Analyze charts, graphs, or visual data\n- **Learning Tool**: Ask questions about anything you see on your screen\n\n## 🚀 Quick Start\n\n### Docker (Recommended)\n\nAdd your API keys in `.env` file:\n\n```bash\ndocker-compose up -d --build\n```\n\nVisit http://localhost:3000\n\nPrerequisites:\n- Docker\n- Node.js (v22 or higher)\n- npm\n\n### Local Setup\n\n1. Clone the repository:\n   ```\n   git clone https://github.com/bigsk1/ai-screen-analyzer.git\n   cd ai-screen-analyzer\n   ```\n\n2. Install dependencies:\n   ```\n   npm install\n   ```\n\n3. Create a `.env` file in the root directory and add your API keys:\n\n   ```env \n   REACT_APP_OPENAI_API_KEY=your_openai_api_key\n   ANTHROPIC_API_KEY=your_anthropic_api_key\n   ANTHROPIC_MODEL=claude-3-5-sonnet-20241022\n\n   OLLAMA_API_URL=http://localhost:11434\n   ```\n\n4. Start the development server:\n   ```\n   npm run dev\n   ```\n\n5. Open your browser and navigate to `http://localhost:3000`.\n\n\u003cbr\u003e\n\u003cbr\u003e\n\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/user-attachments/assets/afc1eb69-37d5-4fef-8ed0-c1e00bce4c02\" width=\"350\" alt=\"AI Screen Analyzer\"\u003e\n  \u003cbr\u003e\n  \u003cem\u003eAI Screen Analyzer in action\u003c/em\u003e\n\u003c/p\u003e\n\n## 🧰 Technologies Used\n\n- **Frontend**: React, Tailwind CSS\n- **Backend**: Node.js, Express\n- **AI Services**: OpenAI API, Anthropic API, Ollama\n- **Containerization**: Docker\n\n## 🔧 Configuration\n- Add your API keys in `.env` file\n- To change the default Anthropic model, update the `ANTHROPIC_MODEL` variable\n- For Ollama, the default URL is `http://localhost:11434` when running natively, and `host.docker.internal:11434` in Docker\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbigsk1%2Fai-screen-analyzer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbigsk1%2Fai-screen-analyzer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbigsk1%2Fai-screen-analyzer/lists"}