Skip to main content

SmythOS Runtime Environment (SRE)

The SmythOS Runtime Environment (SRE) is the execution platform for agents.
It abstracts away infrastructure so you can focus on logic, workflows, and scaling securely.

View the SRE on GitHub

Why SRE matters

SRE provides a consistent runtime across local, cloud, and hybrid deployments.
It includes modular connectors, a unified API surface, and security controls built into the core runtime.

Key Features

FeatureWhat it gives you
Agent-centricPurpose-built runtime for agent execution rather than generic compute
Unified interfaceOne API for storage, language models, caching, and connectors
Modular connectorsSwap or extend providers without rewriting workflows
Secure by defaultZero-trust access, credential management, and isolation
ObservableLogs, monitoring, and step-level debugging available out of the box
Cloud-nativeWorks the same locally, in the cloud, or hybrid environments
ScalableRuns efficiently from prototype to enterprise workloads

How to Build with SRE

You can use SRE through different interfaces. Choose the one that fits your workflow:

MethodBest forHow you’ll use it
StudioVisual prototyping, collaborationOpen Studio and design workflows with a drag-and-drop canvas.
SDKDevelopers, CI/CD pipelinesUse the TypeScript SDK to create, configure, and extend agents programmatically.
CLIAutomation, scripting, power usersScaffold, run, and manage agents from the terminal.

See Building Agents for help deciding which interface to start with.

Architecture Overview

SRE is modular. Each subsystem handles one core aspect of the runtime.
You can replace or extend subsystems depending on your requirements.

SubsystemWhat it manages
IOData I/O, storage, API routing, and logging
LLM ManagerLanguage model access, caching, and usage tracking
SecurityCredentials, authentication, secrets, and access policies
Memory ManagerAgent state, caching layers, and conversation context
Agent ManagerExecution, lifecycle management, monitoring, and orchestration

Security Model

SRE enforces zero-trust access control.
Every action and resource is scoped to an agent identity with explicit permissions.

const candidate = AccessCandidate.agent(agentId);
const storage = ConnectorService.getStorageConnector().user(candidate);
await storage.write('data.json', content);

See the Security Model for details, or explore examples in the SRE GitHub repo.

Development to Production

You can begin building agents immediately. SRE initializes automatically in local development with no setup required:

async function main() {
// agent logic here
}
main();

When you need enterprise-grade features, you can configure external vaults, cloud storage, logging, or scaling connectors. The same agent definitions work across local, staging, and production environments.

See Enterprise Deployment for advanced configuration examples.

What’s Next