Put your AI agent online (and what an AI agent is)

What an AI agent is, in plain words, and how to put yours online with memory, a password and a spending cap. Your coding agent builds and runs it on aidrop.it.

An AI agent is a program where an AI model decides the next step and uses tools to finish a task, not just answer a question. A chatbot tells you how to reschedule a booking. An agent looks up the booking, checks the calendar and moves it. This page puts an agent your coding agent (Claude Code, Codex or Cursor) wrote for you online, with memory, a password and a spending cap. You paste one paragraph; your coding agent does the building on aidrop.it.

What you will have at the end

Your agent at its own web address, answering around the clock.
A simple chat page, plus a way for your website or other tools to call it.
Conversations kept in a database, so a restart does not wipe them.
A password in front of it, so strangers cannot run up your bill.
A monthly spending limit at your AI provider as a second safety net.

Words you will meet

API key: a password from an AI company (Anthropic, OpenAI) that lets your agent use its models. Every call is billed to you.
Agent SDK: a ready-made toolkit for building agents, such as the Claude Agent SDK or the OpenAI Agents SDK.
Database: where the agent writes things down so they survive restarts. aidrop.it runs one for your project.
Secret: a key aidrop.it keeps for your project and hands to the app when it starts. It never goes into the code.

What you need

An aidrop.it account with your coding agent connected. See Quickstart.
A plan that includes a database: Trial, Pro or above. Starter has none. Prices are on aidrop.it.
For the Claude Agent SDK, the 1 GB size, which starts at Pro. Anthropic suggests about 1 GB of memory per running agent.
An API key and a monthly spending limit at your provider. At Anthropic, set the limit on a separate workspace; the default one cannot have a limit. At OpenAI, set a project spend limit and switch on the hard limit, or calls continue past it.

Say this to your agent

Put my AI agent online as an aidrop.it Service. Read aidrop.it's runtime
rules before writing anything and follow them.

What it does: [DESCRIBE THE AGENT AND ITS TOOLS].
Built with: [Claude Agent SDK / OpenAI Agents SDK / plain API calls].

- A small HTTP chat endpoint plus a minimal chat page, and a health
  endpoint that answers without calling the model.
- The address is public: require a long random access key on every
  request except health.
- Keep conversation history in the Project's PostgreSQL. Check what the
  Project already has first and ask me before creating a new instance.
  The app's disk is wiped on every restart, so nothing that must last
  may live in files.
- If you use the Claude Agent SDK: point its home and config folder at
  the temporary folder, and keep sessions in PostgreSQL through a
  SessionStore adapter. Size 1 GB.
- Cap each request: a maximum number of turns and of output tokens.
- All outbound calls go through the platform's HTTP proxy. Make sure the
  HTTP client honours it; Node's built-in fetch does not by default.
- Model API key and access key as Project secrets, never in the repo.

Push it, build it, and tell me the address, the access key's secret
name, and how to call it from my website.

What your agent does

Reads aidrop.it’s rules, then writes the chat page, the address other programs call, and the password check.
Checks whether your project already has a database, and asks you before creating one.
Saves the code in a new repository on aidrop.it.
Asks you for the keys. Give them to the agent, or type them on the Project Secrets page in the aidrop.it dashboard.
Builds the app and waits until it runs. If it fails, it reads the error log, fixes the code and builds again.
Gives you the address and tells you how to use it.

Check that it works

Open the address, enter the access key and give the agent a real task.
Open it in a private window without the key. It refuses.
Ask your coding agent to restart the app, then continue the chat. The agent still remembers what you said.
Your AI provider’s usage page shows the calls you just made.

Keep it safe and affordable

The address is open to the whole internet from the first deploy. Without the access key, anyone who finds it can use your agent on your bill. Keep the key long and random, and ask your coding agent for a new one if it leaks.

The provider’s spending limit is the backstop: past it, the provider stops answering and your agent shows an error instead of a bigger bill. More on keys: where do the secrets live.

aidrop.it keeps no copies of your database; your coding agent makes a backup when you ask (how).

When something goes wrong

What you see	What to tell your agent
The build is green but the app never starts	“Read the logs. The ‘I’m alive’ page must answer without calling the model.”
Every answer is a timeout or connection error	“Make the model calls go through the platform’s HTTP proxy.”
It forgets the conversation after a restart	“Keep the chat history in the database, not in files.”
The agent says it has no API key	“Check the model key secret is stored and named for this app.”
Strangers can use it	“Require the access key on every request.”
The provider says the limit is reached	Nothing to fix. Raise the limit at the provider, or wait for next month.

FAQ

What is an AI agent, in one sentence?

A program where an AI model picks the next step and uses tools, such as search, a calendar or your database, until the task is done. A chatbot only replies; an agent acts, so it needs limits on what it touches and spends.

What is an AI agent platform?

A service that runs agents for you: it keeps them online, stores their keys and memory, and shows what they did. Some build the agent in a visual editor; others host code you or your coding agent wrote.

Do I need an agent SDK?

No. A simple agent is a loop: send the conversation to the model, run the tool it asks for, send back the result, repeat. An SDK writes that loop for you. The Claude Agent SDK gives you the same tools and loop that power Claude Code, so it needs more memory than a plain loop.

Where should my agent run?

Anywhere that stays on and keeps its data in a database. On aidrop.it your coding agent builds it, stores its keys, gives it a database and hands you the address, without you touching a server.