I can’t try Background Agents yet because they aren’t available in Privacy Mode. I’m curious if—and how—they’ll roll this out to others, given their guarantee that no code is stored on their servers. According to their security page [1], about 50% of users have Privacy Mode enabled.
I’m also curious how this compares to OpenAI’s Codex. In my experience, running agents locally has worked better for large or complex codebases, especially since setting up the environment correctly can be tricky in those setups.
I’m also curious how this compares to OpenAI’s Codex. In my experience, running agents locally has worked better for large or complex codebases, especially since setting up the environment correctly can be tricky in those setups.
[1] https://www.cursor.com/security#privacy-mode-guarantee