Alp Adur

I had this issue where i really did not like the when i had many terminals open at the same time - when you try to code with 6+ agents at the same time, across, say, 3 projects, you get huge context fragmentation. I am a visual person, and its way easier for me to remember where things are if I placed them there - I build this 2D canvas for myself initially and then decided to open-source - the main goal there is to let me (or the user) to place the terminals, github trees (to track agent's progress across branches on different repos), beads issues tables across many machines all on the same screen. Most important note, once again, is since its a 2D canvas, it feels more like a citybuilder where i I decide where to put stuff and thus remember exactly where what is running. It boosts my efficiency by couple pp at the very least (anecdotal, can be placebo!!);

I also ended up using it nearly daily for couple months now... My friend, who helps with dev, and I had to focus on other things (life) but now we are kinda coming back to the app to implement coworking feature.

@myradism Thanks for the detailed feedback. A few of these are actually things we’re already working on.

For GPU and resource usage, we’re working on more granular telemetry so you can see which agent/process is actually consuming CPU, RAM, and VRAM instead of just looking at system-wide numbers. We’re also looking at better handling for agents that switch between local compute and external inference APIs.

On the canvas side, we’re working on improving virtualization and batching for high-frequency updates. The goal is for the workspace to stay responsive even when you have 20+ agents running and multiple terminals producing output at the same time.

We’re also exploring per-agent resource limits and scheduling, so you can actually control how much CPU/RAM/GPU each agent is allowed to use. That becomes pretty important once you start running larger workloads on a single machine.

Some of this is already in development and some is still being tested, but these are definitely areas we want to improve as we push 49Agents toward larger multi-agent setups.

Really appreciate you taking the time to give such detailed feedback. It gives us a pretty good list of things to go after next.

Additionally, we are experimenting with coworking on the same workspace right now, and we are looking for testers/contributors!!

@cloud i think this comment is AI... There is an mdash and the general way it sounds