You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I see some references to protocol support for remote ACP agents, but not much discussion. I'm curious if we can surface it here or elsewhere.
Some of the benefits i see of running a remote ACP agent are:
Access to development dependencies that are only present, or easier to integrate with, on the remote systems (non windows/*nix compilers and error feedback, macro preprocessing, source control managers)
Access to remote file systems; There are various strategies to work with remote files that may not integrate well with an ACP agents pre-requisites around file system access. Incorporating MCP tools may be one way to give an agent the ability to work with remote files (i havent tested how well this approach would work in practice). Running the agent on a remote system with access to the remote file system may be more straight forward or better suited.
Potential for analyze-code-test cycles without being intermediated by a workstation IDE toolsets exposed over MCP
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
I see some references to protocol support for remote ACP agents, but not much discussion. I'm curious if we can surface it here or elsewhere.
Some of the benefits i see of running a remote ACP agent are:
Beta Was this translation helpful? Give feedback.
All reactions