Initialization Overview
Solace Agent Mesh provides multiple ways to initialize a new project:- GUI Mode (Recommended): Browser-based configuration interface
- Interactive CLI Mode: Step-by-step command-line prompts
- Non-Interactive Mode: Automated setup with command-line options
GUI Initialization
The easiest way to get started is using the web-based initialization interface:Launch GUI Initialization
From your project directory, run:This will start a web server on port 5002 and open your browser automatically.
Configure Broker Settings
Choose one of three broker options:
- Existing Solace Broker: Connect to a running Solace PubSub+ broker
- New Local Container: Launch a new Solace broker using Docker/Podman
- Dev Mode: Run all components in a single process (development only)
Configure LLM Settings
Provide your LLM configuration:
- Endpoint URL: API endpoint (e.g.,
https://api.openai.com/v1) - API Key: Your provider’s API key
- Planning Model: Model for complex reasoning (e.g.,
openai/gpt-4o) - General Model: Model for general tasks (e.g.,
openai/gpt-3.5-turbo)
Configure Orchestrator Agent
Set up your main orchestrator:
- Agent Name: Name for your orchestrator (default:
OrchestratorAgent) - Streaming Support: Enable real-time streaming responses
- Artifact Service: Choose storage backend (filesystem, memory, S3, GCS)
- Session Service: Configure session persistence (memory, SQL)
Optional: Web UI Gateway
Configure the chat interface:
- Enable/Disable: Add a web UI for interacting with agents
- Port: Default is 8000
- Bot Name: Customize the chatbot name
- Welcome Message: Set initial greeting
Interactive CLI Initialization
For a traditional command-line experience:-
Broker Configuration
-
LLM Configuration
- LLM Service Endpoint URL
- LLM Service API Key (hidden input)
- Planning Model Name
- General Model Name
-
Project Settings
- Namespace (default:
solace_app/) - Agent name
- Artifact and session service configuration
- Namespace (default:
The interactive mode allows you to review and modify each setting before proceeding.
Non-Interactive (Skip) Mode
For automated deployments or CI/CD pipelines, use skip mode with command-line options:Generated Project Structure
After initialization, your project will have the following structure:Configuration Files
shared_config.yaml
Contains shared settings used across all components:main_orchestrator.yaml
Defines the orchestrator agent configuration:CLI Options Reference
Broker Options
| Option | Description | Default |
|---|---|---|
--broker-type | Broker type: 1/solace, 2/container, 3/dev | 1 |
--broker-url | Broker WebSocket URL | ws://localhost:8008 |
--broker-vpn | Message VPN name | default |
--broker-username | Broker username | default |
--broker-password | Broker password | default |
--container-engine | Container engine: docker or podman | Auto-detect |
--dev-mode | Enable dev mode (shortcut for --broker-type 3) | false |
LLM Options
| Option | Description |
|---|---|
--llm-service-endpoint | LLM API endpoint URL |
--llm-service-api-key | LLM API key |
--llm-service-planning-model-name | Model for planning tasks |
--llm-service-general-model-name | Model for general tasks |
Agent Options
| Option | Description | Default |
|---|---|---|
--agent-name | Orchestrator agent name | OrchestratorAgent |
--supports-streaming | Enable streaming | true |
--artifact-service-type | Storage: memory, filesystem, s3, gcs | filesystem |
--artifact-service-base-path | Filesystem storage path | /tmp/samv2 |
--artifact-service-scope | Scope: namespace, app, custom | namespace |
--session-service-type | Session storage: memory, sql, vertex_rag | sql |
--session-service-behavior | Behavior: PERSISTENT, RUN_BASED | PERSISTENT |
Web UI Options
| Option | Description | Default |
|---|---|---|
--add-webui-gateway | Add Web UI gateway | true |
--webui-fastapi-host | Web UI host | 127.0.0.1 |
--webui-fastapi-port | Web UI HTTP port | 8000 |
--webui-fastapi-https-port | Web UI HTTPS port | 8443 |
--webui-frontend-bot-name | Bot display name | Solace Agent Mesh |
--webui-frontend-welcome-message | Welcome message | How can I assist you today? |
Advanced Configuration
S3 Artifact Storage
To use S3 for artifact storage:PostgreSQL for Sessions
To use PostgreSQL instead of SQLite:OAuth Authentication for LLM
For LLM providers requiring OAuth 2.0:Post-Initialization
After initialization completes:Review Generated Files
Check the
.env file and YAML configurations to ensure all settings are correct.Access the Web UI
Open http://localhost:8000 in your browser to interact with your agents.