Tines The single, secure environment for agents, apps, and automations.
tterm
A terminal, a real browser, and Claude Code under one roof
158 followers
A terminal, a real browser, and Claude Code under one roof
158 followers
tterm is a macOS cockpit for working with Claude Code. Every project is a row of explorer, Claude, and file viewer. Stack as many as you're juggling. A real Chromium browser lives inside, and there's no editor on purpose: you review diffs hunk by hunk and commit. It even rebuilds itself. Ask the Claude pane for a feature and the running app hot-reloads with it. No account, no telemetry. Free for hobbyists, on Apple silicon.
Fewer than you'd expect, at least for our shape of work. A cycle here is roughly 40 reads and 5 writes, so the gate fires a handful of times a session and everything else stays fully autonomous. There's no model in the path either, it's a selector and URL allowlist, so the token cost is zero. What actually killed the annoyance was making approval sticky per domain for the session: I confirm the first push and not the next four.
@dipankar_sarkar Very interesting, thanks for sharing!
the browser-session sharing thread here is a great read. curious about the other direction: if I've got two or three project rows stacked for different repos, is each row's Claude pane fully isolated from the others, or could a prompt in one row's context ever end up seeing something from a different project's files or conversation history?
@galdayan Not presently, I could see it being useful for explicit agent-swarm use cases. Will likely not add that feature to the base version though as most users will probably work across different disconnected repos. Thanks for the question!
@tanaygondil makes sense - disconnected repos is probably the right assumption for 90% of users. agent-swarm setups are still niche enough that scoping it out of the base version and leaving it for people to wire up themselves seems like the right tradeoff for now. appreciate the straight answer.
Putting terminal, browser, and Claude Code in one place makes sense if the handoffs stay visible. For shipping work, the valuable layer is checkpoints: what changed, what was verified, what failed, and where the human needs to make the next call.
@krekeltronics agreed! presently, the diff review is meant to be that checkpoint - nothing agent writes lands unless you've reviewed it hunk by hunk. is there anything you'd like to see added in addition to this?
Combining terminal, browser, and Claude Code in one window sounds like it could cut a lot of context-switching. How does it handle screen real estate when all three are active — tabs, splits, or something else?
@ark_y_k On the base version, I use splits - but you're free to configure it however you like!
@tanaygondil Splits sounds like a solid default for staying oriented across terminal, browser, and Claude Code at once. Do you find yourself resizing panes often, or does one layout tend to stick once you've set it up?
@ark_y_k haha I'm very picky (and have poor eyesight) so I tend to resize panes often. I find it to be not much of a chore to do so manually, but I'm planning on adding saved presets!
as a real Chromium browser is bundled in, would love to see a way to save reusable diff-view layouts or presets per project type, makes flipping between code reviews and Claude chats way faster
@hiranurerkasap love the suggestion, gonna def prompt that into my tterm (and you can too!) :)
Finally a Claude wrapper that doesn't try to be an editor. Stacking multiple projects side by side with the diff review built in is exactly what I needed when juggling a few repos at once.
@eyllggerciyevg haha or a cozy youtube video while claude goes at it!
finally a mac app that gets out of the way for claude code, and the hunk-by-hunk diff review is genuinely faster than clicking through vscode. weirdly charmed by the self-rebuild feature too
@doukanywb5 thank you for the kind words :)