Rendered at 15:59:12 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
richardkam0511 9 minutes ago [-]
I actually went down a different path and set it up so my friend and I can use the same agent with approval-gated turns. He's more technical than I am, but I believe I'm better at marketing. We can see both of our prompts and be on the same page. There is also a mode where we can branch off with our own agents.
Watching his prompts made me better at producing my own and using the agent effectively.
carimura 55 seconds ago [-]
That's neat. You could do this with Buzz by just having open room conversations with agents.
aliasxneo 8 minutes ago [-]
Have you thought about browser/machine use at all? I like the idea of Grok Bot but would rather host/maintain it myself with my own agents.
whazor 1 hours ago [-]
I am now on the MCP route, where I have lots of personally hosted MCPs. Including managing calender/e-mail.
It does not cost too much effort to maintain MCP servers. No port forwarding or VPNs required thanks to OpenAI tunnels.
And security wise its quite nice, since you have to activate MCP or give permission sometimes. So each chat is kind of isolated from each-other.
carimura 1 hours ago [-]
interesting.. does that bloat the context window? I imagine Hermes already struggles with context window size.. been meaning to look into that.
Atotalnoob 44 seconds ago [-]
Skills and MCPs CAN bloat the context window. Some harnesses do more progressive loading of skills/mcp depending on how many you have. Check your harnesses docs.
Personally, I feel skills+CLI is better, since only the description of the skill enters the context window until it’s required and CLIs should support help flags which will allow you do have progressive discovery.
And a CLI is also easy to use yourself.
whazor 1 hours ago [-]
I don't have problems on ChatGPT with the amount of MCPs (five) I have. But each MCP can do quite a lot.
orangebread 2 hours ago [-]
Very cool setup. I went down a similar path and while it is definitely cool to see the extent of how agentic AI can be, I agree the ROI isn't _quite_ there yet.
I don't live in a world where I need to be constantly reading and replying to emails, so 95% of my inbox is just subscription spam. With development I need to be at the helm to design the planning requirements and actively make decisions before the agent goes off and executes the plan. But I don't need a personal agent for that, I work directly out of codex/claude-code.
carimura 2 hours ago [-]
same. I'd like to get to a place where I can have long-running tasks and goals for more over-night working, but it's not there yet.
lukasco 42 minutes ago [-]
I've been building a triage agent for my inbox and whatsapp (it's product shaped), which has ironically left me not building one of these. So even while productizing, I'm getting fomo on the full monty.
I've also been building a harness that maintains my apps which I'm hoping to open source.
Hard agree that these things don't have personal ROI, and are actually quite hard to build reliably.
But it's really fun! And having a bot fix a live error is pretty exciting.
gchp 15 minutes ago [-]
Cool! How much does this setup cost you, roughly?
carimura 12 minutes ago [-]
$48/month for the droplet (could probably be cheaper on Hertzner) and $100/month for OpenAI plan. so ~$150/month but again this could be cheaper with a different VPS and using Terra/Luna.
I also have a claude max plan for coding but like I mentioned in the article coding is still separate from the agents.
4lx87 24 minutes ago [-]
Have you experimented with using a single executive agent (instead of multiple agents)?
carimura 22 minutes ago [-]
that was one of my FAQs at the bottom. I want separation of duties and least-privilege so agents can only access what they need for their particular duties.
That said, my vision is to eventually build manager agents to manage the minion agents. Like real people. I have no idea if "people" is the right analogy for all this work but my brain can't really wrap around a different analogy yet.
owencmcgrath 14 minutes ago [-]
The most interesting part of this to me is having an agent that reads logs and spins up fixes in real time.
Great write up!
moribvndvs 1 hours ago [-]
Not pointed at the author, but at the current state of affairs: this is fucking exhausting. We went and made a trillions-dollar market out of the bikeshedding maximization machine.
carimura 1 hours ago [-]
this author agrees. hence my attempt at steering part of that trillion dollars for my non-profit which maybe someday might do some good.
Manfrednotfunny 1 hours ago [-]
No we did not.
LLM was invented and its just clear that this is something someone needs to build.
Why?
Because it makes just sense. You don't want an agent running on a laptop you close. You want to keep context small, you want to split up work / parallize it etc.
I'm now waiting for a while until the open source agent platform emerges and im borderline motivated to build something but i'm not doing it. He did, which is not a crime.
davidw 14 minutes ago [-]
What is the total monthly spend, approximately, on all this; if you don't mind saying, of course?
carimura 11 minutes ago [-]
(copied from comment above)
$48/month for the droplet (could probably be cheaper on Hertzner) and $100/month for OpenAI plan. so ~$150/month but again this could be cheaper with a different VPS and using Terra/Luna.
I also have a claude max plan for coding but like I mentioned in the article coding is still separate from the agents.
tosh 1 hours ago [-]
ty for the writeup!
being able to talk to each of the agents via dm (but also in group chats) sounds interesting
does that mean that you have 1 chat per domain specific agent? can you also start multiple sessions/threads or is that not part of the way you interact with them currently?
carimura 1 hours ago [-]
it's just like Slack really. I have a DM open for each agent where I can talk direct. But they are also part of individual rooms also where I just need to @ them and they open a thread. They can talk to each other also by @'ing each other (in public rooms or ones they both belong to)
It's literally just like humans.. except. not.
tosh 1 hours ago [-]
makes sense, ty
JSR_FDED 1 hours ago [-]
Appreciate the honesty and lack of hype.
geooff_ 2 hours ago [-]
It's always fun seeing how other people are using these tools.
> Has it been worth it? For the journey, yes, for the ROI, nope.
It's also nice seeing someone experiment without succumbing to AI psychosis.
carimura 2 hours ago [-]
i'd like to go into the psychosis but i'm not there yet.
phplovesong 21 minutes ago [-]
I would never have the power to have AI just do everything. I like to create, not have some slop machine do whatever.
carimura 20 minutes ago [-]
AI is far from doing everything in my setup. just looking for incremental wins to see if my slop machine can be useful.
It does not cost too much effort to maintain MCP servers. No port forwarding or VPNs required thanks to OpenAI tunnels.
And security wise its quite nice, since you have to activate MCP or give permission sometimes. So each chat is kind of isolated from each-other.
Personally, I feel skills+CLI is better, since only the description of the skill enters the context window until it’s required and CLIs should support help flags which will allow you do have progressive discovery.
And a CLI is also easy to use yourself.
I don't live in a world where I need to be constantly reading and replying to emails, so 95% of my inbox is just subscription spam. With development I need to be at the helm to design the planning requirements and actively make decisions before the agent goes off and executes the plan. But I don't need a personal agent for that, I work directly out of codex/claude-code.
I've also been building a harness that maintains my apps which I'm hoping to open source.
Hard agree that these things don't have personal ROI, and are actually quite hard to build reliably.
But it's really fun! And having a bot fix a live error is pretty exciting.
I also have a claude max plan for coding but like I mentioned in the article coding is still separate from the agents.
That said, my vision is to eventually build manager agents to manage the minion agents. Like real people. I have no idea if "people" is the right analogy for all this work but my brain can't really wrap around a different analogy yet.
Great write up!
LLM was invented and its just clear that this is something someone needs to build.
Why?
Because it makes just sense. You don't want an agent running on a laptop you close. You want to keep context small, you want to split up work / parallize it etc.
I'm now waiting for a while until the open source agent platform emerges and im borderline motivated to build something but i'm not doing it. He did, which is not a crime.
$48/month for the droplet (could probably be cheaper on Hertzner) and $100/month for OpenAI plan. so ~$150/month but again this could be cheaper with a different VPS and using Terra/Luna.
I also have a claude max plan for coding but like I mentioned in the article coding is still separate from the agents.
being able to talk to each of the agents via dm (but also in group chats) sounds interesting
does that mean that you have 1 chat per domain specific agent? can you also start multiple sessions/threads or is that not part of the way you interact with them currently?
It's literally just like humans.. except. not.
> Has it been worth it? For the journey, yes, for the ROI, nope.
It's also nice seeing someone experiment without succumbing to AI psychosis.