Strands Agents (AWS Agent Core)
Integrate AgentSuite with Strands Agents, the open-source framework that powers AWS Agent Core, via the Virtue Gateway for AgentGuard runtime enforcement, access control, MCP server scanning (where enabled), and session observability in the dashboard.
Installation
pip install agentsuite-sdk[strands]
The [strands] extra installs the core strands-agents package needed for the adapter. It does not include an LLM provider — install the one you need separately:
pip install strands-agents[anthropic] # Anthropic Claude (used in the demo)
pip install strands-agents[openai] # OpenAI
How It Works
adapter.mcp_client()— returns a StrandsMCPClientto pass intoAgent(tools=[...]).adapter.hook_provider()— returns a hook provider to pass intoAgent(hooks=[...])for automatic session tracking.
Quickstart
from strands import Agent
from strands.models.anthropic import AnthropicModel
from agentsuite import GatewayClient
client = GatewayClient(url="...", api_key="sk-vai-...")
adapter = client.strands()
model = AnthropicModel(
client_args={"api_key": "sk-ant-..."},
model_id="claude-sonnet-4-20250514",
max_tokens=4096,
)
agent = Agent(
model=model,
system_prompt="You are a helpful assistant.",
tools=[adapter.mcp_client()],
hooks=[adapter.hook_provider()],
)
agent("What are my open tickets?")
Full runnable example: demo_strands.py
Example Output
The agent responds to the query and prints the session ID:

View the full session trace in the VirtueAgent dashboard (Observability → Sessions):

Environment Variables
| Variable | Description |
|---|---|
VIRTUE_GATEWAY_URL | Gateway MCP endpoint URL |
VIRTUE_API_KEY | VirtueAI API key |
ANTHROPIC_API_KEY | Anthropic API key (only when using Anthropic models) |
AGENT_MODEL | Optional; model name (demo default: claude-sonnet-4-20250514) |