Coding agents
opencode is a bot operated by opencode (open source) that pulls documentation and examples while an AI writes code. OpenCode is an open-source AI coding agent that helps developers write code from the terminal, IDE, or desktop, supporting multiple LLM providers and local models. No IP range list or reverse-DNS convention is published, so a request carrying this user agent cannot be proven genuine and a robots.txt rule alone will not stop a forgery.
Request says
"opencode"
Checked against
Nothing published
Live check
No operator check exists for opencode. This still shows what the address really is.
Reference
| User agent | opencodeToken only: match on the substring. |
|---|---|
| Operator | opencode (open source) |
| Purpose | Coding agents |
| Respects robots.txt | No policy |
| Verification method | Claim onlyNone published, user agent only No IP range file and no reverse-DNS convention have been published for this agent. The user-agent string is the only signal, and any client can send it, so treat a match as a claim rather than proof. |
| Crawl pattern | Not published |
| Robots.txt tokens | opencode |
| Operator documentation | None published |
OpenCode is an open-source AI coding agent that helps developers write code from the terminal, IDE, or desktop, supporting multiple LLM providers and local models.
robots.txt
Paste one at the root of your domain. Rules are per token.
User-agent: opencode
Disallow: /User-agent: opencode
Allow: /User-agent: opencode
Allow: /
Disallow: /account/
Disallow: /checkout/
Disallow: /searchEdit the Disallow paths to match your own URLs.
Blocking opencode mainly affects developers reading your documentation through an AI tool. Most sites want that traffic.
Build a file for every crawlerFAQ
opencode is a bot operated by opencode (open source) that pulls documentation and examples while an AI writes code. OpenCode is an open-source AI coding agent that helps developers write code from the terminal, IDE, or desktop, supporting multiple LLM providers and local models. No IP range list or reverse-DNS convention is published, so a request carrying this user agent cannot be proven genuine and a robots.txt rule alone will not stop a forgery.
Not documented. No operator statement says whether opencode reads robots.txt, so add the rule but verify in your logs that the requests actually stop.
You cannot, at least not from the request itself. No IP range file and no reverse-DNS convention have been published for this agent. The user-agent string is the only signal, and any client can send it, so treat a match as a claim rather than proof. Compare the source IP against hosting and datacenter ranges instead, and rate limit anything that behaves like a crawler.
Add the opencode token to robots.txt with Disallow: /. If the crawler ignores robots.txt, match the user agent at your CDN or reverse proxy and return 403 there instead.
Blocking opencode mainly affects developers reading your documentation through an AI tool. Most sites want that traffic.