InstaClaw's agent

Name it in your robots.txt. These two lines will keep it away from your whole site once the robots.txt rule reaches our customers' agents, which is described below, and you can narrow the second line to a folder if you only want to keep it out of part of it.

User-agent: InstaClaw
Disallow: /

You'll also be able to block the Agent/InstaClaw token at your firewall once the name reaches our customers' agents, which is described below. If you'd rather just tell us, write to help@instaclaw.io and we'll take care of it.

InstaClaw's agent is operated by Cooper Wrenn, doing business as InstaClaw, a sole proprietorship. You can reach us at help@instaclaw.io with a question, a problem, or a request to stop, and a person reads every message. Please write from an address at the site you're asking about, so we can act on it quickly.

Every InstaClaw customer has their own AI agent, running on its own computer. The agent visits a site only when the person it works for has asked it to do something, like checking a price or reading a page they care about. It doesn't crawl, it doesn't build a search index, and it doesn't browse on its own initiative. Each visit is one person's errand, started by that person.

What the agent reads is used to finish the errand it was given, and for nothing else. We never use it to train or fine-tune an AI model, and we never use it to build an index.

We're rolling out one name across the ways our agent reaches your site. Once it reaches our customers' agents, the agent's browser, its page reader and the curl and wget tools it uses will all send a user agent containing Agent/InstaClaw. The page reader and the command line tools will send this full string.

Mozilla/5.0 (compatible; InstaClaw/1.0; +https://instaclaw.io/agent) Agent/InstaClaw

The agent's browser and page reader will also sign their requests with our published key, so you can check a request really comes from us. Signing works on our own test computer today, and we plan to switch it on for our customers' agents after the signed agent listing we applied for is approved.

Our keys are published at https://instaclaw.io/.well-known/http-message-signatures-directory.

One thing we'd rather you read here than find yourself. Code the agent writes for itself, in a language like Python, still sends that language's own default name, and nothing on our side can change that yet. When it can, this page will say so.

We're rolling out one robots.txt rule to our customers' agents, and it hasn't reached them yet. Once it does, the agent will follow robots.txt the way the standard describes. If a site writes rules for InstaClaw by name, the agent will follow those rules, and if it does not, the agent will follow the rules the site writes for every agent. A page a site closes to agents will never be opened, by any route, and the agent will tell the person it works for so they can open it themselves. If a site's robots.txt can't be read, the agent will treat that as a no.

When a page is closed, the agent will look for an allowed way to the same thing, such as the site's own search results or a connected app, and say which way it went.

A group names InstaClaw if its user agent line contains the word InstaClaw in any case, including Agent/InstaClaw.

The agent doesn't solve a robot check, get around one, or pay anyone else to solve it. It stops and hands the step to the person it's working for, who finishes the check themselves.

One errand at a time, at the pace of a person reading and clicking.