[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-73536":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":27,"readmeContent":28,"aiSummary":29,"trendingCount":16,"starSnapshotCount":16,"syncStatus":30,"lastSyncTime":31,"discoverSource":32},73536,"open-deep-research","nickscamara\u002Fopen-deep-research","nickscamara","An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl","https:\u002F\u002Ffirecrawl.dev\u002Fextract",null,"TypeScript",6247,740,29,37,0,1,6,20,3,39.61,"Other",false,"main",true,[],"2026-06-12 02:03:14","# Open Deep Research\n\nAn Open-Source clone of Open AI's Deep Research experiment. Instead of using a fine-tuned version of o3, this method uses [Firecrawl's extract + search](https:\u002F\u002Ffirecrawl.dev\u002F) with a reasoning model to deep research the web.\n\nCheck out the demo [here](https:\u002F\u002Fx.com\u002Fnickscamara_\u002Fstatus\u002F1886459999905521912)\n\n![Open Deep Research Hero](public\u002Fopen-hero.png)\n\n## Features\n\n- [Firecrawl](https:\u002F\u002Ffirecrawl.dev) Search + Extract\n  - Feed realtime data to the AI via search\n  - Extract structured data from multiple websites via extract\n- [Next.js](https:\u002F\u002Fnextjs.org) App Router\n  - Advanced routing for seamless navigation and performance\n  - React Server Components (RSCs) and Server Actions for server-side rendering and increased performance\n- [AI SDK](https:\u002F\u002Fsdk.vercel.ai\u002Fdocs)\n  - Unified API for generating text, structured objects, and tool calls with LLMs\n  - Hooks for building dynamic chat and generative user interfaces\n  - Supports OpenAI (default), Anthropic, Cohere, and other model providers\n- [shadcn\u002Fui](https:\u002F\u002Fui.shadcn.com)\n  - Styling with [Tailwind CSS](https:\u002F\u002Ftailwindcss.com)\n  - Component primitives from [Radix UI](https:\u002F\u002Fradix-ui.com) for accessibility and flexibility\n- Data Persistence\n  - [Vercel Postgres powered by Neon](https:\u002F\u002Fvercel.com\u002Fstorage\u002Fpostgres) for saving chat history and user data\n  - [Vercel Blob](https:\u002F\u002Fvercel.com\u002Fstorage\u002Fblob) for efficient file storage\n- [NextAuth.js](https:\u002F\u002Fgithub.com\u002Fnextauthjs\u002Fnext-auth)\n  - Simple and secure authentication\n\n## Model Providers\n\nThis template ships with OpenAI `gpt-4o` as the default. However, with the [AI SDK](https:\u002F\u002Fsdk.vercel.ai\u002Fdocs), you can switch LLM providers to [OpenAI](https:\u002F\u002Fopenai.com), [Anthropic](https:\u002F\u002Fanthropic.com), [Cohere](https:\u002F\u002Fcohere.com\u002F), and [many more](https:\u002F\u002Fsdk.vercel.ai\u002Fproviders\u002Fai-sdk-providers) with just a few lines of code.\n\nThis repo is compatible with [OpenRouter](https:\u002F\u002Fopenrouter.ai\u002F) and [OpenAI](https:\u002F\u002Fopenai.com\u002F). To use OpenRouter, you need to set the `OPENROUTER_API_KEY` environment variable.\n\n## Function Max Duration\n\nBy default, the function timeout is set to 300 seconds (5 minutes). If you're using Vercel's Hobby tier, you'll need to reduce this to 60 seconds. You can adjust this by changing the `MAX_DURATION` environment variable in your `.env` file:\n\n```bash\nMAX_DURATION=60\n```\n\nLearn more about it [here](https:\u002F\u002Fvercel.com\u002Fdocs\u002Ffunctions\u002Fconfiguring-functions\u002Fduration#duration-limits)\n\n## Deploy Your Own\n\nYou can deploy your own version of the Next.js AI Chatbot to Vercel with one click:\n\n[![Deploy with Vercel](https:\u002F\u002Fvercel.com\u002Fbutton)](https:\u002F\u002Fvercel.com\u002Fnew\u002Fclone?repository-url=https%3A%2F%2Fgithub.com%2Fnickscamara%2Fopen-deep-research&env=AUTH_SECRET,OPENAI_API_KEY,OPENROUTER_API_KEY,FIRECRAWL_API_KEY,BLOB_READ_WRITE_TOKEN,POSTGRES_URL,UPSTASH_REDIS_REST_URL,UPSTASH_REDIS_REST_TOKEN,REASONING_MODEL,BYPASS_JSON_VALIDATION,TOGETHER_API_KEY,MAX_DURATION&envDescription=Learn%20more%20about%20how%20to%20get%20the%20API%20Keys%20for%20the%20application&envLink=https%3A%2F%2Fgithub.com%2Fvercel%2Fai-chatbot%2Fblob%2Fmain%2F.env.example&demo-title=AI%20Chatbot&demo-description=An%20Open-Source%20AI%20Chatbot%20Template%20Built%20With%20Next.js%20and%20the%20AI%20SDK%20by%20Vercel.&demo-url=https%3A%2F%2Fchat.vercel.ai&stores=[{%22type%22:%22postgres%22},{%22type%22:%22blob%22}])\n\n## Running locally\n\nYou will need to use the environment variables [defined in `.env.example`](.env.example) to run Next.js AI Chatbot. It's recommended you use [Vercel Environment Variables](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fprojects\u002Fenvironment-variables) for this, but a `.env` file is all that is necessary.\n\n> Note: You should not commit your `.env` file or it will expose secrets that will allow others to control access to your various OpenAI and authentication provider accounts.\n\n1. Install Vercel CLI: `npm i -g vercel`\n2. Link local instance with Vercel and GitHub accounts (creates `.vercel` directory): `vercel link`\n3. Download your environment variables: `vercel env pull`\n\n# 1. First install all dependencies\n```bash\npnpm install\n```\n\n# 2. Then run database migrations\n```bash\npnpm db:migrate\n```\n\n# 3. Run the app\n```bash\npnpm dev\n```\n\nYour app template should now be running on [localhost:3000](http:\u002F\u002Flocalhost:3000\u002F).\n\n\n# Models dependencies\n\nIf you want to use a model other than the default, you will need to install the dependencies for that model.\n\n\nTogetherAI's Deepseek:\n```bash\npnpm add @ai-sdk\u002Ftogetherai\n```\n\nNote: Maximum rate limit https:\u002F\u002Fdocs.together.ai\u002Fdocs\u002Frate-limits\n\n## Reasoning Model Configuration\n\nThe application uses a separate model for reasoning tasks (like research analysis and structured outputs). This can be configured using the `REASONING_MODEL` environment variable.\n\n### Available Options\n\n| Provider | Models | Notes |\n|----------|--------|-------|\n| OpenAI | `gpt-4o`, `o1`, `o3-mini` | Native JSON schema support |\n| TogetherAI | `deepseek-ai\u002FDeepSeek-R1` | Requires `BYPASS_JSON_VALIDATION=true` |\n\n### Important Notes\n\n- Only certain OpenAI models (gpt-4o, o1, o3-mini) natively support structured JSON outputs\n- Other models (deepseek-reasoner) can be used but may require disabling JSON schema validation\n- When using models that don't support JSON schema:\n  - Set `BYPASS_JSON_VALIDATION=true` in your .env file\n  - This allows non-OpenAI models to be used for reasoning tasks\n  - Note: Without JSON validation, the model responses may be less structured\n- The reasoning model is used for tasks that require structured thinking and analysis, such as:\n  - Research analysis\n  - Document suggestions\n  - Data extraction\n  - Structured responses\n- If no `REASONING_MODEL` is specified, it defaults to `o1-mini`\n- If an invalid model is specified, it will fall back to `o1-mini`\n\n### Usage\n\nAdd to your `.env` file:\n```bash\n# Choose one of: deepseek-reasoner, deepseek-ai\u002FDeepSeek-R1\nREASONING_MODEL=deepseek-ai\u002FDeepSeek-R1\n\n# Required when using models that don't support JSON schema (like deepseek-reasoner)\nBYPASS_JSON_VALIDATION=true\n```\n\nThe reasoning model is automatically used when the application needs structured outputs or complex analysis, regardless of which model the user has selected for general chat.\n","Open Deep Research 是一个开源的深度网络研究项目，通过Firecrawl工具从网页中提取大量数据，并使用推理模型进行分析。其核心功能包括利用Firecrawl实时搜索和提取结构化数据、基于Next.js的应用路由提供高级导航和性能优化、以及通过AI SDK支持多种语言模型提供商如OpenAI、Anthropic等，实现文本生成与用户界面构建。此外，该项目还采用了shadcn\u002Fui提供的Tailwind CSS样式和Radix UI组件以增强可访问性和灵活性，并通过Vercel Postgres和Blob服务保证了聊天记录及用户数据的安全存储。此项目适用于需要对互联网上的广泛信息进行深入研究与分析的场景，比如市场调研、学术研究等领域。",2,"2026-06-11 03:46:01","high_star"]