titanium2099 / scira

Scira (Formerly MiniPerplx) is a minimalistic AI-powered search engine that helps you find information on the internet. Powered by Vercel AI SDK! Search with models like Grok 2.0.

Scira

A minimalistic AI-powered search engine that helps you find information on the internet.

Powered By

• Vercel AI SDK - For AI model integration and streaming
• Tavily AI - For search grounding and web search capabilities

Special Thanks

Warp, the intelligent terminal

Available for MacOS and Linux
Visit warp.dev to learn more

Features

• AI-powered search: Get answers to your questions using Anthropic's Models.
• Web search: Search the web using Tavily's API.
• URL Specific search: Get information from a specific URL.
• Weather: Get the current weather for any location using OpenWeather's API.
• Programming: Run code snippets in multiple languages using E2B's API.
• Maps: Get the location of any place using Google Maps API, Mapbox API, and TripAdvisor API.
• YouTube Search: Search for videos on YouTube and get timestamps and transcripts powered by Exa.AI - the Web Search API.
• Academic Search: Search for academic papers powered by Exa.AI - the Web Search API.
• X Posts Search: Search for posts on X.com powered by Exa.AI - the Web Search API.
• Flight Tracker: Track flights using AviationStack's API.
• Trending Movies and TV Shows: Get information about trending movies and TV shows.
• Movie or TV Show Search: Get information about any movie or TV show.

LLM used

• xAI's Grok
• Anthropic's Claude 3.5 Sonnet
• Meta's Llama 3.3 70B by Cerebras
• Deepseek R1 Distill by Groq Inc
• OpenAI's o3-mini

Built with

• Next.js
• Tailwind CSS
• Vercel AI SDK
• Shadcn/UI
• Exa.AI
• Tavily
• OpenWeather
• E2B
• Google Maps
• Mapbox
• TripAdvisor
• AviationStack

Deploy your own

Set Scira as your default search engine

1. Open the Chrome browser settings:

   • Click on the three vertical dots in the upper right corner of the browser.
   • Select "Settings" from the dropdown menu.

2. Go to the search engine settings:

   • In the left sidebar, click on "Search engine."
   • Then select "Manage search engines and site search."

3. Add a new search engine:

   • Click on "Add" next to "Site search."

4. Set the search engine name:

   • Enter Scira in the "Search engine" field.

5. Set the search engine URL:

   • Enter https://scira.app?q=%s in the "URL with %s in place of query" field.

6. Set the search engine shortcut:

   • Enter sh in the "Shortcut" field.

7. Set Default:

   • Click on the three dots next to the search engine you just added.
   • Select "Make default" from the dropdown menu.

After completing these steps, you should be able to use Scira as your default search engine in Chrome.

Local development

Run via Docker

The application can be run using Docker in two ways:

Using Docker Compose (Recommended)

1. Make sure you have Docker and Docker Compose installed on your system
2. Create a .env file based on .env.example with your API keys
3. Run the following command in the project root:

   docker compose up

4. The application will be available at http://localhost:3000

Using Docker Directly

1. Create a .env file based on .env.example with your API keys
2. Build the Docker image:

   docker build -t scira.app .

3. Run the container:

   docker run --env-file .env -p 3000:3000 scira.app

The application uses a multi-stage build process to minimize the final image size and implements security best practices. The production image runs on Node.js LTS with Alpine Linux for a minimal footprint.

Run with Node.js

To run the application locally without Docker:

1. Sign up for accounts with the required AI providers:
   • OpenAI (required)
   • Anthropic (required)
   • Tavily (required for web search feature)
2. Copy .env.example to .env.local and fill in your API keys
3. Install dependencies:

   pnpm install

4. Start the development server:

   pnpm dev

5. Open http://localhost:3000 in your browser

License

This project is licensed under the MIT License - see the LICENSE file for details.