OpenClaw announces integration with both ACP and Codex App Server protocols, with potential future support for the Anthropic protocol.

Gate News, March 18 — OpenClaw maintainer Onur Solmaz announced today on the X platform that OpenClaw will support both the Agent Client Protocol (ACP) and OpenAI’s Codex App Server protocol, emphasizing “more interoperability and options.” He also mentioned that if Anthropic develops its own protocol, it will be integrated as well.

Currently, OpenClaw supports programming agents like Codex and Claude Code via the ACP protocol, allowing users to directly invoke these agents in Discord channels and Telegram topics to perform coding tasks. With the addition of support for the Codex App Server protocol, users can experience native Codex functionality within OpenClaw. Developer Harold Hunt showcased a preview of the corresponding plugin, which includes features like task planning guidance and answer revision.

ACP is an open standard adopted by companies like JetBrains and Zed, using JSON-RPC 2.0 to enable communication between agents. The Codex App Server is a conversational protocol designed specifically by OpenAI for Codex, supporting dialogue creation, restoration, and forking. By supporting both protocols, OpenClaw marks its evolution from an AI agent framework toward a unified multi-protocol layer.

View Original
Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to Disclaimer.
Comment
0/400
No comments