Blog

We asked our Hermes agent if it was leaking API keys. It printed one into the chat.

Your Hermes agent keeps API keys in more places than you think, and some go to your AI provider with every message. Swytchcode's free API Key Leak Check finds them in seconds and explains the fix in plain words.

What did your Hermes agent install last week? Now you can check.

Your Hermes AI agent installs packages, pulls containers and clones repos on your behalf, and keeps no record. Swytchcode's free Agent Install Monitor keeps one, privately, on your own machine.

We connected Instinct to a flight API through Swytchcode. Here's how it went

Instinct has no way to plug in custom APIs, so we tried connecting it to Duffel's flight API through a Google Sheet, with Swytchcode holding the keys and the rules. How it works, and an honest look at how Swytchcode did.

I tested 10 self-hosted AI agents against our guardrails. Here's what we had to change.

Making API calls boringly reliable

Retries, idempotency, and settings that survive upgrades.

A Prompt Is Not a Policy: guardrails and human approval for AI agents

Your agent wants to refund $5,000. Who says yes?

The model decides. The call layer executes.

Why always-on agents like OpenClaw and Hermes need a strict layer between the model's decisions and your APIs.

Your API, Your OAuth App, Your Rules

How we split custom OAuth apps from private APIs, and what happened to providers already downloaded to customers' machines.

Designing a CLI for AI agents, not humans

What an agent should see, what it shouldn't, and how to fail in a way it can recover from.

CreateOS Integration Is Now Live on Swytchcode

CreateOS is now live on Swytchcode. Build production-ready AI agents with CreateOS Sandbox APIs for isolated execution and Swytchcode for reliable, secure access to real-world APIs.

Connect Fintech APIs to Claude

Give Claude access to Stripe, PayPal, Square, and other payment APIs without handing over raw keys. Auth, retries, policies, and guardrails stay with you.

Building a Production-Ready AI Agent Integration with SwytchCode: A Complete Hands-On Guide

"swy exec" Explained: Inputs, Outputs, and Exit Codes

How swy exec works: the single execution path for running Swytchcode tools, either by canonical ID or by plain-English intent.

How to Set Up Policy Guardrails for AI Agents with Swytchcode

How to use Swytchcode's guard policies to control exactly what an AI agent is allowed to execute, enforced before any request leaves your machine.

tooling.json, manifest.json, and policies.json Explained: Swytchcode's Config Files

What tooling.json, manifest.json, and policies.json actually do in a Swytchcode project, and which CLI commands read and write each one.

How Swytchcode Retries Failed API Calls

A look at how Swytchcode automatically retries failed API calls with backoff, and why that retry logic is safe by default instead of risky.

Idempotency Explained: How Swytchcode Prevents Duplicate Charges and Duplicate Emails

Idempotency stops a retried API call from repeating its side effect. Here's what that means and how Swytchcode applies it automatically to every tool call.

What Is an Execution Layer? Why AI Agents Need One

An execution layer sits between an AI agent and real APIs, handling authentication, retries, and policy checks. Here's what that means and why it matters.

Connect Swytchcode to LangGraph: Setup Guide and Example

Connect Swytchcode to LangGraph so your stateful agent workflows can safely call real APIs, with authentication, retries, and policy checks built in.

Connect Swytchcode to the Anthropic SDK: Setup Guide and Example

Connect Swytchcode to the Anthropic SDK so Claude can safely call real APIs in your application. Full setup steps and a working code example.

Connect Swytchcode to the OpenAI Agents SDK: Setup Guide and Example

Connect Swytchcode to the OpenAI Agents SDK so your agent can safely call real APIs, with authentication, retries, and policy checks handled automatically.

How to Connect Swytchcode to OpenClaw: Setup Guide

Learn how to connect Swytchcode to OpenClaw so your AI assistant can safely call real APIs, plus a real working multi-API onboarding demo built with HubSpot, Stripe, and Resend.

How to Connect Swytchcode MCP Server: Setup Guide for Cursor, Claude Code, Windsurf & More

Learn how to connect the Swytchcode MCP server to Cursor, Claude Code, Windsurf, Copilot, and other AI editors, with exact setup commands, verification steps, and fixes for common connection issues.

Different Ways to Use Swytchcode: CLI, MCP, and SDK Guide

Swytchcode can be used through the CLI, MCP, or native SDKs. This guide breaks down each method with setup steps, code examples, and guidance on which one fits your workflow.

How to build a Github AI Agent

Explore about how you can build a github AI Agent bot with swytchcode cli