Now running in 42 regions

Ship agents to production in one command.

Strandsagents Cloud runs your agents close to your users. Tracing, secrets, guardrails, and autoscaling come built in, so you write the agent and skip the infrastructure.

99.99%
Measured uptime, trailing 12 months
42
Regions with active routing
38ms
Median cold start
2.4B
Tool calls served each month

Platform

Everything an agent needs, already running.

You bring the model and the tools. Strandsagents Cloud handles where the agent runs, how it scales, and what you can see afterward.

Edge deployment in 42 regions

Each request goes to the nearest healthy region. If one region fails, traffic moves in under 200 ms.

Secrets vault

Store API keys once. Agents read them at runtime and never write them to logs or images.

Scale to zero

Idle agents cost nothing. Replicas start in under a second when traffic arrives.

Traces for every run

Each model call, tool call, and token count is traced by default. Open any run and see why the agent chose a tool.

Guardrails

Redact personal data, block unsafe tool inputs, and cap spend per user before a request reaches a model.

Canary rollouts

Send a small share of traffic to a new version first. Roll back in one command if error rates rise.

How it works

From a Python file to a live endpoint.

Three steps. No Dockerfile, no YAML, and no cluster to size.

01

Install the SDK

Add the package to your project with one command.

pip install strandsagents
02

Write the agent

Define the model, the tools, and the guardrails in plain Python.

agent.py
03

Deploy

Run one command. The agent is live in every region within seconds.

strandsagents deploy

Developer experience

Your agent, in plain Python.

Tools are ordinary functions with type hints. Strandsagents Cloud reads the signatures, builds the tool schema, and wires up tracing.

  • Works with any major model provider
  • Tool schemas generated from your type hints
  • Deploys straight from your repository
  • Rollbacks in one command
# agent.py
from strandsagents import Agent, tool

# Tools are plain Python functions.
@tool
def lookup_order(order_id: str) -> dict:
    """Fetch an order from the warehouse."""
    return warehouse.get(order_id)

agent = Agent(
    model="claude-sonnet",
    tools=[lookup_order],
    guardrails=["pii-redaction"],
    max_spend_per_user=0.50,
)

agent.deploy(regions="auto", min_replicas=0)

Pricing

Start free. Pay when agents earn.

Every plan includes tracing, secrets, and all 42 regions.

Hobby

For side projects and experiments.

$0/ month
  • 3 agents
  • 100k tool calls per month
  • Community support
Start free

Enterprise

For regulated workloads and large fleets.

Custom
  • Private regions
  • SSO and audit logs
  • Dedicated support engineer
  • Custom SLA
Talk to sales

Your next agent can be live before lunch.

Deploy the demo agent in one command and open its traces in the console.