> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentset.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Step 1: Local Setup

> Clone the repository and configure your local development environment

First, you'll need to clone the Agentset repo and install the dependencies.

<Steps>
  <Step title="Clone the repo">
    First, clone the [Agentset repo](https://github.com/agentset-ai/agentset).

    ```bash Terminal theme={null}
    git clone https://github.com/agentset-ai/agentset.git
    ```
  </Step>

  <Step title="Install dependencies">
    Run the following command to install the dependencies:

    ```bash Terminal theme={null}
    pnpm i
    ```
  </Step>

  <Step title="Set up environment variables">
    Convert the `.env.example` file to `.env`. You can start filling in the first few environment variables:

    ```bash Terminal theme={null}
    # Default vector database (used when users select the Agentset managed option)
    DEFAULT_PINECONE_API_KEY=pcsk_xxx
    DEFAULT_PINECONE_HOST="https://xxx.svc.xxx-xxx-xxx.pinecone.io"

    # Cohere API key (used for re-ranking)
    DEFAULT_COHERE_API_KEY=xxx

    # Default models (used when users select the Agentset managed option)
    DEFAULT_AZURE_RESOURCE_NAME=xxx
    DEFAULT_AZURE_API_KEY=xxx
    DEFAULT_AZURE_EMBEDDING_DEPLOYMENT=text-embedding-3-large
    DEFAULT_AZURE_LLM_DEPLOYMENT=gpt-4.1

    # Trigger.dev secret key (for workflow orchestration)
    TRIGGER_SECRET_KEY=tr_dev_xxx
    ```

    <Note>
      We currently use azure openai models as the default (when users pick the Agentset managed option). If you'd like to change that, update `apps/web/src/lib/embeddings.ts` and `apps/web/src/lib/llm.ts` to use a different provider.
    </Note>

    You will fill in the remaining environment variables in the following steps.
  </Step>
</Steps>

## Next Steps

Once you've completed the local setup, proceed to [Step 2: Upstash](/open-source/step-2-upstash) to set up your Redis database and queue management.