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.
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)
The observability stack (logs, metrics, traces) is often an afterthought but should be a first-class architectural concern. You cannot improve what you cannot measure, and you cannot debug what you cannot observe.
It was more of a tool for myself but some interest from others inspired me so iterating on it. People interested in this kind of thing should join my slack! https://monetworkspace.com/terminal
I have two claude code subscriptions: a team plan through my employer and I'm paying for the $200/month plan outside of that.
Trading $200/month of my money for the ability to build all of the things I've been thinking about for years is a great trade for me. I've built more things for fun/potential profit in the last year than I did in the previous decade combined.
And of course, one of the things I've built is a version of what OP made that works exactly how I want it to work. :)
I build my own products and services and the effective ROI for paying for a more or less unlimited max Claude Code plan is fairly ridiculously positive.
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
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.
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?
I've built my own as well, in a terminal. Not pretty, but does the job until something better comes along (maybe Baton is that something better): https://github.com/electrovir/agent-storm
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?
Yeah perfect example, the main thing I _would_ use multiple agents on is optimizing/benchmarking code, but for that you specifically can't use worktree, you need one agent per machine or they'll taint each other's benchmarks
I have tried to provide after best ability, but have only been testing them on vm's on my mac! So be aware. I labeled them Beta due to this. But most features should work fine, probably better on linux than windows.
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
The underlying git worktree still lives on your disk until you delete it. So its not harder than starting a terminal with claude --continue, or codex resume --last inside the git worktree, depending on what agent the user used.
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.
I have seen teams spend months fine-tuning retrieval algorithms when the real issue was that their ingestion pipeline was feeding HTML boilerplate into the vector store. Fix the input first.
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.
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.
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)
https://t3.codes
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?
The fun part being it worked on mobile too: https://youtube.com/shorts/CmemwDGwpx8?si=xzAJBb8ha7DLIDmY
It was more of a tool for myself but some interest from others inspired me so iterating on it. People interested in this kind of thing should join my slack! https://monetworkspace.com/terminal
Trading $200/month of my money for the ability to build all of the things I've been thinking about for years is a great trade for me. I've built more things for fun/potential profit in the last year than I did in the previous decade combined.
And of course, one of the things I've built is a version of what OP made that works exactly how I want it to work. :)
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
Let a thousand vibecoded flowers bloom
I appreciate that you provided multiple OS versions rather than just go for Mac only like some.
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
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.
It’s blank. Lots of blank gray rectangles too. Site is broken?
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.