our biggest release ever is now available to everyone in @cursor_ai here's a rundown of what's new in 0.50 ↓
a new tab model with support for multi-file edits and more natural editing flow
we're releasing background agent in preview that will allow you to run multiple agents in parallel on a remote vm at any point, you can view the status, send a follow-up, or take over
a refreshed inline edit (cmd/ctrl+k) with full file edit capability and agent handoff
include your entire codebase with @-folder. if it does not fit, you'll see an icon on top of files and folders that indicates and explains this
work in multiple codebases with workspaces click file → add folder to workspace and include all the projects you need to have in context. you can also save this configuration as json from the menu and reopen the same setup later
chat got multiple upgrades: you can now export and duplicate them for when you want to share and explore different paths, as well as adjusting font size
we’ve updated our pricing to be simpler and more unified. all model calls now count as requests, and Max Mode is available for every frontier model with token-based billing (20% on top of API pricing)
other improvements including - MCP on WSL & remote SSH, - toggleable MCP tools - streamable HTTP for MCP - native agent terminal (instead of emulated) and more
we heard your feedback and have been hard at work, hope you enjoy this one! read the full changelog here: https://www.cursor.com/changel...



