Ask HN: How many AI agents do you actively use?
I have around four for talking through ideas and three active coding agents. None of them are truly long-running.
Is that typical? How many agents are you using regularly, and are any of them running autonomously for hours?
I have a tmux split in 4 panes, 4 agents running in 4 workspaces with shared memory. Most of the times I use 2 concurrently, but here and there I have extra analysis or reviews to do. I like this setup with tmux, works over ssh, easy to bring any one full focus, etc.
do you use git worktrees also then?
no, for now just multiple copies of the same repo. typically the agents work on independent things.
but I will try. the limit tbh is me and my ability to keep up with what’s happening. I work mainly on security/cryptography so I’m expected to audit the results of my work very carefully.
I run multiple fable/opus and sol sessions for both chat and coding- I read a lot of academic papers and it grew to a point where I needed to use a reference management system like zotero to keep track of it. So I recently one-shotted a ~1000 pdf literature review folder into a .bibtex file to import into zotero. . Includes multi-step DOI extraction and multi-review steps to reduce false positives. Also can check patents via EPO API. And can interact programmatically with zotero via its API to add tags, notes etc. Very specific to my requirements and codex sol max did it in a single 8-hr goal session with very few bugs
I'm obviously biased, but I'm building aq.dev, a shared workspace for running coding agents with a team, so I watch a lot of people's sessions more than my own haha.
If I'm between meetings, then I'm really watching 1-2 max. There could be a few others running in the background, but those I'm not paying attention to that much.
If I'm coding and in the zone, then usually 4-5 workspaces with 1-3 agents per workspace.
I watch a lot of people's sessions more than my own haha
That's not a good thing if you want people to use your service.
I rarely call multiple AI agents at the same time, because I often get the context wrong (such as talking about the needs of project B in project A), and I feel that the parallel ability of the human brain is very limited.
I use Codex, which defaults to 1 agent and automatically dispatches more when handling complex tasks. That's more than enough for me
Depends on how you define agents. I use CodeRabbit all the time but it has a swarm of dozens of sub-agents. So am i using 1 agent or 10+?
6-8 running nearly 24/7, any more than that and there's too much for me to review
What kind of stuff are you doing with these agents?
Software development and running simulations. Not totally autonomously, I have 20 years experience as a developer and I review and edit all the code and simulation results, so it's not really me "handing off" the work, it's the LLMs executing the ideas, compiling the results and then presenting back to me.
I dont think they can be fully autonomous yet, I still need to guide them.
I just use 1... been using Kimi and it’s been great.
1 (not long running)
0
At least 4
whatever codex spawns and uses