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.
> Best of luck with this but I think with so many open source agent managers cropping up
What’s the top 5 (or any N) that come to mind:
A) GUI based
B) terminal based
C) web based?
Like, not just personal projects but something with a bit of a community around it? I remember Conductor from a bit ago (seems only Mac is supported) and a few other HN posts but all of those seemed smaller and more barebones. Oh I guess OpenCode also has a desktop and web version, but it never worked well for me (and I need something that can just use headless Claude Code instances).
Asking because I just use Claude Code desktop for organizing my sessions and am a bit behind in that regard - if there are indeed many options that others can vouch for somewhat, I’d love to hear about them!
Edit: apparently there is Cmux (Mac only), T3 Code (very new), Agent Orchestrator (tries to be a weird kanban board), Agor (tries to be a weird canvas board) and Claude Squad (TUI only), but none of those are quite what I'm looking for. If there's all that many options, I might have missed most of them - since Baton or OpenCode (a revisit of it) seem more like what I'd be looking for, maybe Conductor if not Mac only.
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. :)
It’s so funny to me that every AI user feels the need to add this entire disclaimer about how it’s actually helping them build the Starship Enterprise from scratch or whatever every time someone even hints at it maybe being a little bit of a waste of money.
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.
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
Everyone is building the things that are just stop gaps: tui/terminal/cli as foundation for UI, worktree instead of jj workspaces. Rust, tauri or python. You all will discover that after the easy fun parts are done you are rebuilding an IDE and at that point why not try to make Vscode better.
- vscode can run as a webapp in a container no electron needed
- vscode supports workspaces, main arguments i hear is vscode assumes one project per window which is just not the case. i have a folder with all my projects/repos that is open as one workspace in vscode
- visualJJ is the best worktree/workspace manager that no one is talking about, i wish it was open source but there is currently no alternative i am aware of
Not many parts are missing to make this perfect for the use cases all the agent managers try to address, but unlike all these hacks this can evolve one extension at a time and i dont have to throw away all the things that my vscode setup has
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?
You could zoom out a bit and rephrase the question.
Your great-aunt Ida died and left you a consulting team of ten pretty good software engineers. The team's contracts all just ended, so starting tomorrow they'll be idle. Ida said you must run the business for at least two years (fortunately, overhead is already paid for), or forfeit your share of the inheritance. After that you can keep going or liquidate it.
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
You’re seeing that primarily because it’s what people can show off easily. Side projects they do for fun.
I use all of this stuff daily at work. Normally, I’m working on 2 to 4 features in parallel (so worktrees). This might not be simultaneously, but it’s at least across days or weeks.
Skills, agents, tasks, etc are really about creating repeatability in certain parts of my workflow without needing to be hands on.
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 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
Interesting approach to managing multiple agents. We built a GitHub App that does deterministic review of dependency graphs alongside doc review. It catches broken imports and security boundary crossings mathematically, not just opinion. Works well for reviewing agent-generated code.
Spreading agents across git worktrees sounds awesome right up until the merge step. Sure, they're isolated on the filesystem, but when five parallel Claudes rewrite the exact same base class or interface for their own local needs, you're gonna end up with a merge conflict no neural net could ever untangle. All that saved time will just get burned manually rebasing this parallel chaos. Props for a cool pet project, but conceptually this is an architectural dead end
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?
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'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
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)
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
52 comments
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.
> Best of luck with this but I think with so many open source agent managers cropping up
What’s the top 5 (or any N) that come to mind:
A) GUI based
B) terminal based
C) web based?
Like, not just personal projects but something with a bit of a community around it? I remember Conductor from a bit ago (seems only Mac is supported) and a few other HN posts but all of those seemed smaller and more barebones. Oh I guess OpenCode also has a desktop and web version, but it never worked well for me (and I need something that can just use headless Claude Code instances).
Asking because I just use Claude Code desktop for organizing my sessions and am a bit behind in that regard - if there are indeed many options that others can vouch for somewhat, I’d love to hear about them!
Edit: apparently there is Cmux (Mac only), T3 Code (very new), Agent Orchestrator (tries to be a weird kanban board), Agor (tries to be a weird canvas board) and Claude Squad (TUI only), but none of those are quite what I'm looking for. If there's all that many options, I might have missed most of them - since Baton or OpenCode (a revisit of it) seem more like what I'd be looking for, maybe Conductor if not Mac only.
https://github.com/instructkr/claw-code
Here's the oh-my-openagent that is also name checked in the link above:
https://ohmyopenagent.com/
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. :)
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
- vscode can run as a webapp in a container no electron needed
- vscode supports workspaces, main arguments i hear is vscode assumes one project per window which is just not the case. i have a folder with all my projects/repos that is open as one workspace in vscode
- visualJJ is the best worktree/workspace manager that no one is talking about, i wish it was open source but there is currently no alternative i am aware of
Not many parts are missing to make this perfect for the use cases all the agent managers try to address, but unlike all these hacks this can evolve one extension at a time and i dont have to throw away all the things that my vscode setup has
Your great-aunt Ida died and left you a consulting team of ten pretty good software engineers. The team's contracts all just ended, so starting tomorrow they'll be idle. Ida said you must run the business for at least two years (fortunately, overhead is already paid for), or forfeit your share of the inheritance. After that you can keep going or liquidate it.
What do you do?
I use all of this stuff daily at work. Normally, I’m working on 2 to 4 features in parallel (so worktrees). This might not be simultaneously, but it’s at least across days or weeks.
Skills, agents, tasks, etc are really about creating repeatability in certain parts of my workflow without needing to be hands on.
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
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.
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?
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
I couldn't see the pricing page tho.
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
I appreciate that you provided multiple OS versions rather than just go for Mac only like some.
> Features
It’s blank. Lots of blank gray rectangles too. Site is broken?