HN Explorer

Show HN: Baton – A desktop app for developing with AI agents (getbaton.dev)

62 points by tordrt ↗ HN
Hi,

I built this because running multiple Claude Code agents across multiple IDE and terminal windows was getting messy. Like many, I went from working at one thing at the time, to multiple, and it was all changing quite fast.

I needed one place to see all my agents and worktrees, seamlessly switch between them, monitor their status and once their done, review their changes. I also wanted to quickly spin up new agents in isolated worktrees whenever an idea came to mind.

I've been building Baton from within Baton for a while now, which has been a pretty fun loop. Would love to hear what you think!

41 comments

[ 2.9 ms ] story [ 56.3 ms ] thread
twostorytower
Congrats on your launch! How is this different than Conductor?
FrankRay78
If nothing else, I see that Conductor is currently Mac only.
giwook
Would be curious if it is more polished than Conductor. Memory leaks and random bugs seem to crop up in Conductor far too often.
tordrt
The main difference is that Baton is agent-agnostic and terminal-native. It doesn't add a GUI on top of Claude Code or Codex, it builds around the terminal itself, so you run whatever agent CLI you want natively, but with convenient shortcuts for launching them. Which is a nicer experience in my view, but people have different views on this.

Baton is also more git-aware. Instead of just showing raw diff line counts, you see commits ahead and behind your target branch, so you can tell at a glance how far each workspace has diverged and shortcuts for resolving it in the matter you want.

One thing I think is unique is the built-in MCP server. It lets agents spawn new workspaces programmatically, so you use an agent to launch agents in new isolated workspaces.

toastal
> Features

It’s blank. Lots of blank gray rectangles too. Site is broken?

sausajez
Please review the site design. Between the thin blue lines appearing & disappearing, and the "television static" in the background I gave up attempting to read anything in the first 30 seconds on the site because my eyes were drawn anywhere other than the content.
throwaw12
This looks impressive!

How do you restore the state from the old workspaces? do you spawn tmux and resume the conversation or do you do it differently? from the video it felt like instant

riskable
How can people afford to use Claude Code like this‽ Is everyone just playing with it on their employer's dime or what?
saberience
Nice work! Congrats on the release, did you check out Vibe-Kanban or Emdash which are both building in this space?

https://www.emdash.sh/

https://vibekanban.com/

What is your secret sauce, so to speak? I personally built my own local tools and system for this, I tried vibekanban but didn't feel like it added much to my productivity, haven't tried emdash yet.

Renaud
Nice tool for working multiple sessions without them tripping over each-other.

I appreciate that you provided multiple OS versions rather than just go for Mac only like some.

BrandiATMuhkuh
Very cool. And congrats on the launch.

I started to use superset 2 days ago. Which seems similar. It's pretty nice: https://superset.sh

Fyi: here are some things I would like to have for such a tool - notification when an agent is done - each tabs/space has its own terminal, browser, agent - each tab/space runs in a sandbox (eg docker) - each tab/space can run my dev server. But must not conflict with the other dev servers running - each tab/space has a mcp server for the built in browser

Nice to have: - remote access against my machine/tabs - being able to make screenshots

ismail
I have not done much multi-agent development. Trying to understand what problem this solves, surely one can spin up multiple terminal tabs?
flippyhead
This looks great. How do you compare to cmux?
ale
I don’t know how to phrase this without sounding like an arrogant idiot but seriously: what are people actually programming with agents + worktrees + harnesses + tasks + skills + whatnot? Most workflows I see people adopt involve large amounts of infrastructural fluff only to (more) quickly generate what I (anecdotally) have seen is somewhere between code generation of boilerplatish React/laravel/your-fav-framework components for web or native, and niche toy apps for mostly personal use. My very limited usage of agents has been for scanning large (bloated) codebases to get rid of unused code, meaning time consuming and tedious tasks. But it seems the general trend is that programmers just want faster horses?
KurSix
People are just playing around with parallel agents because it looks cool on Twitter. In real prod, 90% of your time isn't spent typing lines of code, it's spent trying to figure out implicit business requirements and debugging undocumented legacy spaghetti. Agents sitting in isolated worktrees are completely useless here - they'll just rapidly and in parallel write code that completely fails to solve the actual business problem
ninininino
Are agents at worktree level or can a single agent and chat work on a parent directory above multiple worktrees of different repos?
mellosouls
Best of luck with this but I think with so many open source agent managers cropping up, you are going to need to provide very special USP to have people choose yours over the free and open versions.

I guess I would suggest that should be a priority for your site and documentation, to help devs understand what that value offer is.

Your site does seem nicely presented though and clarity in capability is possibly an early win over some of the more chaotic documentation elsewhere.

causal
I'm confused, I've been running parallel agents on different worktrees within a single view of Claude Desktop for at least a month. I don't see any new features here?
ohnoesjmr
Maybe I'm daft, I watched the video, and I just didn't understand what this is, or why I'd use it.

Seems like just tabs of claude code, plus markdown viewer which can just be another tab (with an editor) in a tabbed terminal?

My ide supports multiple terminal tabs, plus is a project aware code viewer, and has the ability to run the project.

What would I gain by using this?

kristianc
Theo's t3code does a lot of this for free I think. Interested to know if it uses the same trick for accessing Claude without violating their TOS.

https://t3.codes

ericol
This looks dangerously close to cmux but with a narrower focus (Just Claude code)

BTW, the claude app kind supports this with the /remote-control command, and that was what made me move away from cmux (I still have to start the sessions there)