# Create Your First Agent Once Agent Manager is installed, you can create your first agent from the console. ## Choose an Agent Type[​](#choose-an-agent-type "Direct link to Choose an Agent Type") 1. Navigate to **Agents** in the left sidebar. 2. Click **Add Agent**. 3. Choose how you want to get started: * **Externally-Hosted Agent** — Connect an agent already running outside the platform. WSO2 Agent Manager provides observability and governance without managing the deployment. * **Platform-Hosted Agent** — Deploy and manage the full agent lifecycle directly on WSO2 Agent Manager, including build, deployment, scaling, and observability. *** * Externally-Hosted Agent * Platform-Hosted Agent ## Register an Externally-Hosted Agent[​](#register-an-externally-hosted-agent "Direct link to Register an Externally-Hosted Agent") Fill in the **Agent Details** form: | Field | Description | | ---------------------------- | -------------------------------------------------------- | | **Name** | A display name for your agent (e.g., `Customer Support`) | | **Description** *(optional)* | A short description of what this agent does | Click **Register** to complete the registration. The agent will appear in your agent list and start receiving observability data once you instrument it using the [AMP instrumentation](/agent-manager/docs/v0.15.x/components/amp-instrumentation/.md) package. ## Create a Platform-Hosted Agent[​](#create-a-platform-hosted-agent "Direct link to Create a Platform-Hosted Agent") ### Step 1: Choose a Source Type[​](#step-1-choose-a-source-type "Direct link to Step 1: Choose a Source Type") Select how the agent source will be provided: * **Source Code** — Point to a GitHub repository containing your agent code. The platform builds and deploys it automatically. * **Agent Catalog** — Pick a pre-built agent kind from the Agent Catalog. ### Step 2: Fill in Agent Details[​](#step-2-fill-in-agent-details "Direct link to Step 2: Fill in Agent Details") Provide a **Name** (e.g., `Customer Support Agent`) and an optional **Description**. ### Step 3: Repository Details *(Source Code only)*[​](#step-3-repository-details-source-code-only "Direct link to step-3-repository-details-source-code-only") | Field | Description | | --------------------- | ---------------------------------------------------------------------- | | **GitHub Repository** | Full URL of your repository (e.g., `https://github.com/username/repo`) | | **Branch** | Branch to build from (default: `main`) | | **Project Path** | Path within the repository where the agent code lives (default: `/`) | #### Using a Private Repository[​](#using-a-private-repository "Direct link to Using a Private Repository") If your repository is private, you need to provide a **Git Secret** that contains a GitHub Personal Access Token (PAT). 1. In the **Git Secret** dropdown, select an existing secret or click **+ Create New** to add one. 2. When creating a new secret, provide a **Name** and paste your GitHub PAT. The token must have `repo` scope to allow the platform to clone your private repository. 3. The secret is stored securely and reused across agents that need access to the same repository or organization. ### Step 4: Build Details *(Source Code only)*[​](#step-4-build-details-source-code-only "Direct link to step-4-build-details-source-code-only") Choose a build type: * **Python** — Provide a **Start Command** (default: `python main.py`) and select the **Language Version** (e.g., `3.11`). Dependencies are auto-installed from `requirements.txt`, `pyproject.toml`, or `package.json`. * **Docker** — Use a `Dockerfile` in the repository. **Enable auto instrumentation** *(Python only, checked by default)* Automatically injects OpenTelemetry tracing into your agent for observability with zero code changes. You can also pin the **AMP Instrumentation Version** used by the init container. ### Step 5: Select an Agent Type[​](#step-5-select-an-agent-type "Direct link to Step 5: Select an Agent Type") Choose how your agent receives requests: | Agent Type | Description | | -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Chat Agent** | Standard chat interface. Exposes `POST /chat` on port `8000`. Request: `{message: string, session_id: string, context: JSON}` — Response: `{response: string}` | | **Custom API Agent** | Custom HTTP API. Specify your own OpenAPI specification and port configuration. | ### Step 6: Configure LLM Providers *(Optional)*[​](#step-6-configure-llm-providers-optional "Direct link to step-6-configure-llm-providers-optional") Click **+ Add** to bind one or more LLM providers to this agent. LLM providers are configured separately — see [Register an LLM Service Provider](/agent-manager/docs/v0.15.x/tutorials/register-llm-service-provider/.md). ### Step 7: Set Environment Variables *(Optional)*[​](#step-7-set-environment-variables-optional "Direct link to step-7-set-environment-variables-optional") Add any environment variables your agent requires at runtime. Mark sensitive values as **Secret** to store them securely. ### Step 8: Mount Files *(Optional)*[​](#step-8-mount-files-optional "Direct link to step-8-mount-files-optional") Mount configuration files or other static files into your agent's container at runtime. 1. Click **+ Add File Mount**. 2. Fill in the following fields for each file: | Field | Description | | -------------- | ------------------------------------------------------------------------------------------------------------- | | **File Name** | A unique name to identify the file (max 253 characters) | | **Mount Path** | Absolute path where the file will be available inside the container (e.g., `/workspace/config/settings.yaml`) | | **Content** | The file content (max 1 MB) | | **Sensitive** | Toggle on to store the content as a secret | Duplicate file names are not allowed. Click **Deploy** to build and deploy the agent. *** ## What's Next?[​](#whats-next "Direct link to What's Next?") | Tutorial | Description | | ---------------------------------------------------------------------------------------------------------------------- | --------------------------------------------- | | [Observe Your First Agent](/agent-manager/docs/v0.15.x/tutorials/observe-first-agent/.md) | Set up OpenTelemetry tracing for your agent | | [Register an AI Gateway](/agent-manager/docs/v0.15.x/tutorials/register-ai-gateway/.md) | Connect an LLM provider via the AI gateway | | [Register an LLM Service Provider](/agent-manager/docs/v0.15.x/tutorials/register-llm-service-provider/.md) | Add and configure LLM providers | | [Secure Agent Endpoints with API Keys](/agent-manager/docs/v0.15.x/tutorials/secure-agent-endpoints-with-api-keys/.md) | Protect endpoints with API key authentication | | [Evaluation Monitors](/agent-manager/docs/v0.15.x/tutorials/evaluation-monitors/.md) | Automate quality checks for your agents | | [Custom Evaluators](/agent-manager/docs/v0.15.x/tutorials/custom-evaluators/.md) | Build and deploy your own evaluators | | [Configure Agent LLM Configuration](/agent-manager/docs/v0.15.x/tutorials/configure-agent-llm-configuration/.md) | Bind LLM config to a specific agent |