SmythOS Runtime Environment is an open-source runtime and software development kit for building and running AI agents. Developers use it to create, orchestrate, and manage agents across local, cloud, and edge environments, with abstractions for language models, vector databases, storage, and caching. The catalogue add-ons support work with this runtime.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/smythos/sre/00-creating-agentsgit clone --depth 1 https://github.com/SmythOS/sreWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/smythos/sre/00-creating-agents)<a href="https://agentmods.dev/agents/smythos/sre/00-creating-agents"><img src="https://agentmods.dev/badge/agents/smythos/sre/00-creating-agents.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01246 |
| Opus 5 | $0.00000 | $0.00623 |
| Sonnet 5 | $0.00000 | $0.00249 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
00-creating-agents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Agents
The SmythOS SDK offers flexible ways to create and configure agents. This guide covers everything from basic agent creation to advanced model configuration.
The example scripts in examples/01-agent-code-skill, examples/02-agent-smyth-file, and examples/03-agent-workflow-components provide hands-on illustrations of all the concepts covered here.
Code-Based Agent Creation
You can define agents programmatically by instantiating the Agent class with configuration options:
import { Agent } from '@smythos/sdk';
const agent = new Agent({
id: 'crypto-assistant', // Optional: unique identifier
name: 'CryptoMarket Assistant',
behavior: 'You are a crypto price tracker...',
model: 'gpt-4o', // The language model to use
});
Configuration Options:
id(optional): A unique identifier for the agent. Useful for persistence and tracking.name: A descriptive name for the agent.behavior: Instructions that define the agent's persona and role.model: The language model to use (see Model Configuration below).mode(optional): Agent execution mode. See Agent Modes.
Importing from .smyth Files
For complex agents with visual workflows created in the SmythOS Builder, you can import pre-configured .smyth files:
import { Agent, Model } from '@smythos/sdk';
import path from 'path';
const agentPath = path.resolve(__dirname, './my-agent.smyth');
const agent = Agent.import(agentPath, {
model: 'gpt-4o', // Override the model
teamId: 'team-123', // Optional: specify team context
});
The .smyth file format allows you to define complex workflows with multiple components, skills, and integrations visually, then import them into your code with full programmatic control.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 130 lines · 0 tokens per session scan A c102381f23d7
00-creating-agents is an agent published in the GitHub repository SmythOS/sre (1,289 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,246 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
context
Agents often require more than a list of messages to function effectively. They need context.
memory
LangGraph supports two types of memory essential for building conversational agents.
multi-agent
A single agent might struggle if it needs to specialize in multiple domains or manage many tools. To tackle this, you can break your agent into smaller, independent agents and composing them into a multi-agent system.
tools
Tools are a way to encapsulate a function and its input schema in a way that can be passed to a chat model that supports tool calling. This allows the model to request the execution of this function with specific inputs.
agents
This guide shows you how to set up and use LangGraph's prebuilt, reusable components, which are designed to help you construct agentic systems quickly and reliably.
run_agents
Agents support execution using either .invoke() for full responses, or .stream() for incremental streaming of the output. This section explains how to provide input, interpret output, enable streaming, and control execution limits.