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

# Overview

> Curated, deployment-ready project templates for Agentic AI Applications

Starters are curated, deployment-ready project templates that help teams build and deploy agentic AI applications quickly and consistently.

* **Base template**: A foundational template (`starter-agent-template-agno`) that provides the core structure, configuration, and tooling.
* **Starter kits**: Specialized templates derived from the base template (e.g., `starter-agent`, `starter-multi-agent`) that implement specific agent patterns.

Teams can provision new repositories using **any** of these templates via Self Service, effectively bootstrapping their application with a production-ready setup.

## Why use starters?

<CardGroup cols={3}>
  <Card title="Purpose" icon="bullseye">
    Provide a fast, reliable way to bootstrap agentic AI applications.
  </Card>

  <Card title="Consistency" icon="layer-group">
    Common project layout, configuration, integration, and tooling across all applications.
  </Card>

  <Card title="Extensibility" icon="puzzle-piece">
    Easily extend on top of the template as per the use case.
  </Card>
</CardGroup>

## Base template

The **Agno Base template** is the foundation for all other starters. It implements the core patterns for agent design, API exposure, observability, and configuration.

Use this template if you want a clean slate to build a custom agent architecture while retaining standard platform integrations.

### Available templates

* **Agno Base template** (v0.1.14)
  * Repository: [github.com/bb-ecos-agbs/starter-agent-template-agno](https://github.com/bb-ecos-agbs/starter-agent-template-agno)
  * **Best for**: Custom agent architectures.
* **LangChain Base template**
  * Status: *Coming Soon*

<Note>
  Repositories created from these templates automatically run the **Repository Provisioning Workflow** on first push. See **[CI/CD workflows](/agentic-ai/ci-cd-workflows/repository-provisioning)** for details.
</Note>

Quick scaffold using the Agno template:

```bash theme={"system"}
git clone https://github.com/bb-ecos-agbs/starter-agent-template-agno my-agent
cd my-agent
uv sync
uv run python -m src.main
```

### Project structure

The base template follows a standardized folder structure:

```text theme={"system"}
├── .github/                   # CI/CD workflows
├── promptfoo_config/          # Evaluation configurations
├── prompts/                   # Centralized prompt definitions
├── providers/                 # AI provider configurations
├── src/
│   ├── main.py                # Application entry point
│   ├── agents/                # All agent implementations
│   ├── api/                   # FastAPI routers, schemas
│   ├── config/                # Configuration management
│   ├── logger.py              # Logging setup
│   └── __init__.py
├── tests/                     # Test files
├── redteam.yaml               # Red teaming configuration
├── pyproject.toml             # Dependencies (UV)
├── Dockerfile                 # Container definition
└── README.md
```

### Standard tooling

| Component                     | Tool                                                        |
| :---------------------------- | :---------------------------------------------------------- |
| **Dependency Management**     | UV                                                          |
| **Web Framework**             | FastAPI                                                     |
| **Observability**             | Langfuse, Grafana, or OTLP export (via **bb-ai-sdk 0.1.9**) |
| **AI Gateway**                | Backbase AI Gateway (via **bb-ai-sdk 0.1.9**)               |
| **Evaluation and RedTeaming** | Promptfoo                                                   |

### Built-in CI/CD

All starter kits and templates come pre-configured with standard **[CI/CD workflows](/agentic-ai/ci-cd-workflows/overview)**. These automated pipelines handle:

* **[Linting and Formatting](/agentic-ai/ci-cd-workflows/pull-request-workflow)**: Enforcing code quality standards on every Pull Request.
* **[Testing](/agentic-ai/ci-cd-workflows/pull-request-workflow)**: Running unit and integration tests to ensure reliability.
* **[Docker Builds](/agentic-ai/ci-cd-workflows/build-publish-workflow)**: Building and publishing optimized container images.
* **[Deployment](/agentic-ai/ci-cd-workflows/release-workflow)**: Standardized deployment strategies for releases.

<Tip>
  Learn more about how to manage your agent's lifecycle in the **[CI/CD workflows](/agentic-ai/ci-cd-workflows/overview)** section.
</Tip>

## Available starter kits

These are specialized templates pre-configured with specific agent patterns. Use them to jumpstart development for common use cases.

<CardGroup cols={1}>
  <Card title="Starter agent (level 0)" href="/agentic-ai/starter-kits/starter-agent" icon="robot">
    **Single Agent**: Basic instruction following, reasoning, and tool use. Great for simple tasks.
  </Card>

  <Card title="Multi agent (level 1)" href="/agentic-ai/starter-kits/multi-agent" icon="users">
    **Agent Teams**: Patterns for delegation, collaboration, and coordination between multiple agents.
  </Card>

  <Card title="MCP agent (level 2)" href="/agentic-ai/starter-kits/mcp-starters" icon="plug">
    *(Coming Soon)* **Integration**: Agents pre-wired with Model Context Protocol (MCP) for accessing banking services.
  </Card>

  <Card title="Knowledge Agent (Level 3)" href="/agentic-ai/starter-kits/knowledge-agent" icon="brain">
    **RAG**: Production-ready RAG pipeline with document ingestion, hybrid search, and knowledge-augmented agents.
  </Card>
</CardGroup>

<Tip>
  **How to use**: Select any of these starters (e.g., `starter-agent`, `starter-multi-agent`) as the **repository\_template** in **[Self Service](/agentic-ai/getting-started/self-service)** to provision a new repo with this code.
</Tip>