AgentGrid

Your AI agents team, terminals, notes: one infinite canvas

Developer Tools

Artificial Intelligence

Data Visualization

Visit WebsiteSee on Product HuntTwitter ⧉

one canvas for all your agents is realy usefull, managing a swarm is such a mess rn 🔥 congrats!!

Such a neat launch. Congrats on AgentGrid and best of luck with everything ahead! 🙌

Congrats on the launch! I love the idea of keeping notes and clear context about what is being worked on. I've been using Conductor and have so many workspaces running in parallel I find myself frequently rereading what's happening to remind myself. Hoping AgentGrid will help reduce that!

@Souren Khetcho that supervisor framing is a genuinely different UX problem than the employee one though - a supervisor needs to know when to interrupt you versus when to just log something quietly for later. has that cross-canvas awareness actually changed how proactively the agents surface things, or is it still you pulling status by checking each canvas?

The restart-anxiety story is very relatable, that's the actual reason most people give up on managing multiple agents. Curious about the depth of that persistence though - when you reopen the canvas, does it just restore the pane layout and terminal history, or does it actually resume an in-flight agent task that was mid-tool-call when the restart happened?

very nice - our users love it. you’re clearly onto something. agentic coding requires different tools and AgentGrid is it!!

Huge fan. I’ve been using it for the last month and a half - completely swapped out my use of an IDE. I went from Cursor, to Zed, now using canvas based Claude code/codex sessions in Agent Grid and really loving it.

As a product designer turned design engineer/builder - it’s really working for my spatial memory re: managing the various agent threads I’ve got running across various products. Maybe the best part? You can close it, and all your workspaces and the sessions/nodes are right where you left them. Can’t tell you how much anxiety I had of my IDE crashing and losing all the tabs/terminals I had open. 🤣

Excited to see where Michael and Souren take this.

This makes too much sense. Too much work happening for it to just be in a linear thread!

@Michael Yagudaev that "suck having to go back to single terminal session" bit resonates, once you've had parallel context it's hard to go back to one linear thread of thought. @Souren Khetcho the bash-hunt-for-info framing helps too, sounds less like separate agents and more like one team with shared eyes on the same canvas. does the shared context layer show which agent found what, or does it get flattened once it's fed back in?

been waiting for something like this.

agentgrid could become the default way to run multiple agents. v excited to see what's next.

honestly the persistence is the part that sold me, having every agent and pane restored where you left it is the kind of detail that makes you actually trust the tool instead of fighting it the next morning.

Great launch. A lovely UI. I'm so excited to try this out

What's the maximum number of agents you've seen something running in parallel? Do you have any resources for how we can start maximising our agent usage while not lowering the quality due to the human being the limiter?

the infinite canvas framing for multiple agent terminals is a good fit for how messy multi-agent work actually looks in practice. when two agents on the same canvas need to reference each other's output (one's notes inform the other's next terminal command), is that a manual copy-paste between panes or is there some shared context layer connecting them

The infinite canvas makes juggling multiple agents feel way less chaotic than switching tabs. Restoration across restarts works exactly as advertised, came back and everything was right where I left it.

Souren here! The co-founder who built this to replicate himself LOL

The honest version: I was running so many coding agents at once that I lost track of what was building what. Terminal tabs everywhere. No idea which agent was stuck, which was done, which was quietly burning tokens on the wrong file. I didn't need a better chatbot, I needed to SEE my team.

So I built the canvas. Agents as panes you can watch. A builder here, a QA there, an orchestrator keeping the loop moving, my terminals and browsers sitting right next to them. And the whole workspace survives restarts, which is the feature that finally converted Michael after a month of me pestering him haha

The wildest part for me: My job was mostly reviewing PRs and saying "ship it".

It's free during early access: https://agentgrid.sh

I want your brutal take. What's confusing, what's missing, and what's the first thing you'd have your agent team build? I'm in the comments all day.