LiveKit Hackathon Starter Kits

LiveKit at Gemini 3 SuperHack

Getting Started

LiveKit Agents allow you to quickly create an infinitely customizable voice AI agent in Python or TypeScript.

DO THIS FIRST: Install the LiveKit MCP Server

LiveKit offers a MCP Server that helps coding assistants write code. If you add it to Cursor or Claude Code, the assistants will automatically reference documentation and examples when they're building agents to keep hallicinations to a minimum.

Developer Documentation MCP Server

https://docs.livekit.io/mcp

Install with Cursor

Gemini Starter Kit

A starter kit for building voice and vision agents with Gemini Live API and LiveKit. Get from zero to a working multimodal agent in under 10 minutes. Includes both the agent backend and frontend components.

gemini-live-quickstart

Generic Quick Start with CLI

Using the CLI you can start talking to your agent in 4 steps:

  1. Install the LiveKit CLI: brew install livekit-cli OR curl -sSL https://get.livekit.io/cli
  2. Authenticate with LiveKit Cloud: lk cloud auth
  3. Clone the agent boilerplate: lk app create
  4. Install dependencies and run your agent: cd your_agent_directory && uv sync && uv run src/agent.py download-files && uv run src/agent.py console

Congrats, you're now speaking with your agent!

  • All of your agent code lives in src/agent.py
  • See all of the different agents you can build in the examples repo

Docs quickstart link (includes more copy / paste start from scratch stuff)

Frontend Integration

When you're ready to talk to your agent from the web or mobile app rather than through the console:

  1. Clone the frontend boilerplate: lk app create
  2. Select the template you'd like to clone, ex: agent-starter-react
  3. Move into your directory, then: pnpm install && pnpm dev
  4. Visit the link to talk to your agent
  5. You can also just use a prebuilt sandbox as your frontend

Resources & Repository Links

  • Python Agents: We recommend that you build agents with this framework.
  • Python Examples: See what you can build with these examples.
  • TypeScript Agents: This lightweight Node.js framework doesn't yet include all the features that come bundled with the Python Agents framework.

Billing Information

Deployment

When you're ready to deploy your agent to the cloud:

  • Deploy to cloud w/ livekit agent create from within your agent directory.
  • Test your deployed agents with LiveKit Sandbox or the frontend you cloned above.

Further Resources

To learn more, take a look at our hands-on quickstart for a detailed guide on building and deploying your first agent.

Prize Track

LiveKit is offering a prize of a custom Keychron keyboard to each winning participant of our track!

Track Prompt

The winner of this track will be the team that makes the best use of LiveKit. Use our open source framework and other tools to build an agent that embeds into your application, (or that your application is built around). The winning team will build a functioning agent that uses more complex features of the framework and cloud service to build a unique and technically interesting application.

Requirements

  • Use a LiveKit product.
    • LiveKit voice agent framework: https://github.com/livekit/livekit)
    • LiveKit Cloud: https://cloud.livekit.io/
    • Other products you may find through our website.
  • Feature their use of LiveKit in a major way.
    • Products that use LiveKit in a way that doesn't relate to the main idea of the application probably won't win.

Evaluation Criteria

We will prioritize projects that demonstrate a high level of quality in these categories:

  • Uniqueness
    • Applications that are novel
    • Applications that are using LiveKit in a way we haven't seen before
  • Technical Depth
    • Applications that use more technically difficult or complex features of LiveKit's framework and LiveKit cloud.
    • Applications that use multiple LiveKit products
  • Polish
    • Applications that integrate LiveKit seamlessly.
    • Applications that are easy to use and understand.
    • Applications that use LiveKit to increase the quality of their interfaces.