{"id":31979318,"url":"https://github.com/browserbase/gemini-browser","last_synced_at":"2025-10-14T22:50:41.727Z","repository":{"id":318552951,"uuid":"1054494930","full_name":"browserbase/gemini-browser","owner":"browserbase","description":"Try the new Gemini Computer Use model on Browserbase. ","archived":false,"fork":false,"pushed_at":"2025-10-07T20:50:21.000Z","size":38843,"stargazers_count":8,"open_issues_count":3,"forks_count":2,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-07T22:10:26.692Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://priv-gemini-browser.vercel.app","language":"TypeScript","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/browserbase.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-10T23:37:05.000Z","updated_at":"2025-10-07T22:02:39.000Z","dependencies_parsed_at":"2025-10-07T22:23:03.238Z","dependency_job_id":null,"html_url":"https://github.com/browserbase/gemini-browser","commit_stats":null,"previous_names":["browserbase/gemini-browser"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/browserbase/gemini-browser","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/browserbase%2Fgemini-browser","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/browserbase%2Fgemini-browser/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/browserbase%2Fgemini-browser/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/browserbase%2Fgemini-browser/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/browserbase","download_url":"https://codeload.github.com/browserbase/gemini-browser/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/browserbase%2Fgemini-browser/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279021832,"owners_count":26087059,"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","status":"online","status_checked_at":"2025-10-14T02:00:06.444Z","response_time":60,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":[],"created_at":"2025-10-14T22:50:09.031Z","updated_at":"2025-10-14T22:50:41.720Z","avatar_url":"https://github.com/browserbase.png","language":"TypeScript","readme":"# Gemini CUA Browser\n\n[Demo](https://gemini.browserbase.com)\n\nA powerful browser automation playground powered by Gemini's new Computer Use Agent and Browserbase. This free demo showcases the capabilities of AI-driven browser automation using Stagehand and Gemini's computer-use capabilities.\n\n## Features\n\n- 🤖 **Gemini Computer Use Agent**: Leverages Gemini's `computer-use-preview-10-2025` model for intelligent web interactions\n- 🌐 **Real Browser Control**: Runs on browsers via Browserbase's infrastructure\n- 🎯 **Natural Language Commands**: Describe tasks in plain English and watch the AI execute them\n- 📊 **Real-time Streaming**: Server-Sent Events (SSE) for live agent feedback and progress updates\n- 🔄 **Session Management**: Persistent browser sessions with automatic viewport management\n\n## Tech Stack\n\n### Frontend\n- **Framework**: Next.js 15 with React 19 and TypeScript\n- **Styling**: Tailwind CSS with custom fonts (PP Neue, PP Supply)\n- **Animation**: Framer Motion for smooth transitions\n- **Icons**: Lucide React\n- **Markdown**: ReactMarkdown with GitHub Flavored Markdown (remark-gfm)\n\n### Backend\n- **AI Model**: Gemini Computer Use (`computer-use-preview-10-2025`)\n- **Browser Automation**: Browserbase + Stagehand\n- **Agent Framework**: Stagehand with Playwright Core\n- **Streaming**: Server-Sent Events (SSE) \n- **Runtime**: Node.js with Next.js API routes\n\n### Infrastructure\n- **Analytics**: PostHog for user tracking\n- **Configuration**: Vercel Edge Config for region distribution\n- **Deployment**: Optimized for Vercel with 600s max duration\n\n## Prerequisites\n\n- Node.js 18.x or later\n- pnpm 10.x or later (recommended)\n- API keys:\n  - [Google AI Studio](https://aistudio.google.com/apikey) - for Computer Use Agent\n  - [Browserbase](https://www.browserbase.com) - for browser infrastructure\n\n## Getting Started\n\n### 1. Clone the repository\n```bash\ngit clone https://github.com/browserbase/gemini-browser\ncd gemini-browser\n```\n\n### 2. Install dependencies\n```bash\npnpm install\n```\n\n### 3. Configure environment variables\n```bash\ncp .env.example .env.local\n```\n\nEdit `.env.local` with your credentials:\n```env\n# Google AI Studio API Key\nGOOGLE_API_KEY=your_google_api_key\n\n# Browserbase Configuration\nBROWSERBASE_API_KEY=your_browserbase_api_key\nBROWSERBASE_PROJECT_ID=your_browserbase_project_id\n\n# Optional: Analytics\nNEXT_PUBLIC_POSTHOG_HOST=https://us.i.posthog.com\nNEXT_PUBLIC_POSTHOG_KEY=your_posthog_key\n\n# Optional: Site URL\nNEXT_PUBLIC_SITE_URL=http://localhost:3000\n\n# Optional: Vercel Edge Config\nEDGE_CONFIG=your_edge_config_url\n```\n\n### 4. Start the development server\n```bash\npnpm dev\n```\n\n### 5. Open your browser\nNavigate to [http://localhost:3000](http://localhost:3000)\n\n## Usage\n\n1. **Enter a Command**: Type a natural language instruction or select a preset example:\n   - \"What's the price of NVIDIA stock?\"\n   - \"Review a pull request on Github\"\n   - \"Browse Hacker News for trending debates\"\n   - \"Play a game of 2048\"\n\n2. **Watch the Agent**: The AI will:\n   - Create a browser session\n   - Navigate to relevant websites\n   - Interact with page elements (click, type, scroll)\n   - Take screenshots to verify actions\n   - Stream real-time progress updates\n\n3. **View Results**: See the agent's reasoning, actions, and final response in rich markdown format\n\n## Available Scripts\n\n```bash\n# Development server with Turbopack\npnpm dev\n\n# Production build\npnpm build\n\n# Start production server\npnpm start\n\n# Lint code\npnpm lint\n```\n\n## Contributing\n\nThis is a demo project showcasing Gemini Computer Use Agent capabilities. Feel free to fork and experiment!\n\n## License\n\nMIT\n\n## Acknowledgments\n\n- [Browserbase](https://browserbase.com) - Browser infrastructure and remote browser sessions\n- [Stagehand](https://github.com/browserbasehq/stagehand) - Browser automation framework with AI capabilities\n- [Google AI Studio](https://aistudio.google.com/) - Computer Use Agent API\n- [Vercel](https://vercel.com) - Hosting, edge functions, and edge config\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrowserbase%2Fgemini-browser","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbrowserbase%2Fgemini-browser","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrowserbase%2Fgemini-browser/lists"}