Claude Code Desktop App Redesigned
Run parallel coding agents from one desktop workspace
908 followers
Run parallel coding agents from one desktop workspace
908 followers
Claude Code's desktop app is redesigned for parallel agentic coding. Run sessions across multiple repos, review diffs, edit files, and ship without leaving the app. Built for developers running Claude Code on Pro, Max, Team, or Enterprise.
RiteKit Company Logo API
Using this for MentionFox and FoxAPIs right now and I can say it is a bit unstable, but usable. I have Claude managing it for Claude Code automation. I can say that you have to watch Claude code when automated. It will tell you things are done, but it didn't commit. Buttons that do nothing, pages not JSON'd together...
Running Claude Code solo on Sorti means I context-switch constantly between writing features, debugging, and reviewing , which is not what it was designed for. The parallel session management is the thing I didn't know to ask for. What I'm really curious about is the diff review UX: when you're reviewing changes from multiple agents at once, how does the app surface conflicts or dependencies between their edits? That seems like the genuinely hard problem
Layerpath
Just upgraded @Claude Code Desktop App Redesigned v1.3036.0. If you set any
@Claude by Anthropic env vars for terminal use (API keys, model overrides, custom base URLs), the Desktop app will pick them up and break with cryptic 400 errors.
Then Cmd+Q and relaunch.
Fixed the env bug in 15 minutes. Upgraded to Opus 4.7. Back to building.
the summary view mode is the most underrated part of this. been running claude code for months — verbose output is the constant friction. you end up reading claude's narration instead of the diff. having that as a first-class toggle at the session level, not a system prompt hack, changes the actual workflow.
parallel agents in one workspace is the part i'm most curious about — how do you handle merge conflicts when two sessions touch the same file? does it surface them or just let the last write win?
@tijogaucher git worktrees 🤔
Parallel agent sessions is the part most teams will underestimate — running 2–3 Claude Code instances manually, the kill-shot is losing track of which session edited what. Curious: does the diff review UI group changes by agent or by file, and can you replay a session's reasoning chain when auditing?
been running 2-3 parallel claude code sessions manually for months and the context switching kills focus. if this actually solves isolation + visibility it's a day-1 install for me