Launched this week
49agents IDE
2D IDE for running agents across projects without fatigue
120 followers
2D IDE for running agents across projects without fatigue
120 followers
49Agents IDE is a 2D canvas where every agent, terminal, repo and machine you own lives on a single map that you build yourself. 49 leverages how our brains are wired to solve tab navigation fatigue problem for 10x Engineers - because of the citybuilder-like UX, it becomes effortless to associate processes to tabs, even when you come back to them days later.
49agents IDE
I have been trying to parallelize agentic coding to extreme, sometimes managing up to 15 CLIs at the same time across multiple repos and tasks, and I suffered a huge productivity tax due to context fatigue and constantly forgetting which terminal is doing what. I felt restricted by most grid pane managers, and thats why I started building 49 IDE. I was using it for myself for a while until I showed it to my friend once and he liked it so much that he suggested I open-source it. Since then, we joined efforts to make our IDE solution to context fatigue - for us and other devs.
When we place things on a free canvas, our brains effortlessly associate relative position of the pane to its neighbors, and also associate the context of the task and the project that this specific agent is running. I am not a neurobiologist, but as far as my research went, this is exactly how our brain remember any information - in relation to things around it. We believe this is why 49Agents IDE is so effective.
Later on we also added some quality of life features - ability to track AI usage, connect multiple machines and spawn terminals on them, put the whole thing on private network and then access it from any device, including phone...
We also experimented with claude code state notifications (question/idle/permission requests), but that did not stick as we all moved to using --dangerously-skip-permissions all over...
Additionally, we are experimenting with coworking on the same workspace right now, and we are looking for testers/contributors!!
Is beads actually part of the scheduling model or is it just another pane? i.e. could I eventually have "take every ready issue with no unresolved deps and allocate one agent session per issue"?
49agents IDE
@program_dogihno today it's closer to integrated task context than a giant autonomous scheduler. but what you're describing is exactly why Beads is interesting to us. dependency-aware ready work gives you a much better primitive for agent workflows than throwing random tickets at N shells
49agents IDE
@program_dogihno hey Dog Ihno!
There is no IDE-wide context-ready concierge agent right now who could do that. That being said, it is really easy to build something like that given how everything is already interconnected in the backend. Right now you can click on an issue on the issues table, then click on any terminal, and that agent will be assigned this issue - both the agent's task will be given to solve the issue (basic pasting of instruction into the chat) and at the same time the IDE will know that this terminal is associated with this issue. Then, if you hover over that same issue again in the table, you will see that terminal highlighted.
Check it out, and please share more thoughts - this concierge thing is really cool, we just never hit enough "demand" on that from users to build it out...
How does 49Agents handle a workspace with dozens of active agents without the canvas becoming too crowded?
49agents IDE
@julian_ting2 the canvas is zoomable so you can zoom out and treat terminals more like status indicators than terminals you need to read. you mostly care about which ones are working, idle, waiting for permission etc, then zoom into the one that actually needs your attention.
we're also working on better grouping/collapsing because at some point infinite canvas != infinite human attention :)
49agents IDE
@julian_ting2 That is the whole point!! The canvas is so flexible that there are infinite ways to cluster things around. Here is an example image with many tabs:
49agents IDE
@julian_ting2 and here is a less of a marketing material image from my real workflow
Gamifier for HubSpot
Interesting.
It is just like https://agentkavor.com, but remote.
This is awesome and as open source should have more upvotes!!
Before I get a chance to try this out I am curious, when you are zoomed out etc.. is there an alert / visual system for being able to easily tell which agents / sessions are idle versus which ones are still working?
the crowding question above is the real one. every spatial tool i have used falls over around 30 objects, and the ones that survive it use decay rather than zoom, so anything untouched for a week shrinks on its own and the map stays legible without gardening.
49agents IDE
@rabnoor_s thanks for the comment! yes this is exactly why we created this product. we truly believe that 49agents can solve multiplexing between terminals
@murad_ismayilov2 the multiplexing framing is right, and the thing i would watch is what happens at thirty tabs. spatial tools stay legible through decay rather than zoom, so untouched things shrink on their own.
I've been trying to use crux for agent stuff and my main problem isn't terminal multiplexing anymore, it's context multiplexing. after like 8 claude/codex sessions every tab titlw becomes semantically useless. spatial layout is weirdly much better at encoding "what is this process FOR"
49agents IDE
@selin7 this distinction is exactly what pushed us toward 49. multiplexing shells is solved. multiplexing a bunch of semi-autonomous work is a different problem.