I don’t think you can get the same satisfaction out of these tools if what you want to do is not novel.
If you are exploring the space of possibilities for which there are no clear solutions, then you have to think hard. Take on wildly more ambitious projects. Try to do something you don’t think you can do. And work with them to get there.
let me take a shot. i have thought about both for a while.
dspy is declarative. you say what you want.
dspy says “if you can say what you want in my format, I will let you extract as much value from current LLMs as possible” with its inference strategies (RLM, COT; “modules”) and optimizers (GEPA).
gas town is …
given a plan, i will wrangle agents to complete the plan. you may specify workflows (protomolecules/molecules) that will be repeatedly executed.
the control flow is good about capturing delegation. the mayor writes plans, and polecats do the work. you could represent gas town as a dspy program in a while loop, where each polecat loops until its hooked work is done. when work is finished, its sent to the merge queue and integrated.
gas town uses mostly ephemeral agents as the units for doing work .
you could in theory write gas town with dspy . the execution layer is just an abstraction . gas town operates on beads as state . you could funnel these beads thru a dspy program as well.
the parallels imo are mostly just structured orchestration .
i hope this comes off as sane. 2026 will be a fun year.
Haha, yes, when read out loud, all the new terms do come off as a bit unhinged. :]
It sounds like the major difference is that DSPY is more of a "define a node in a graph of computation, flow data through those nodes". While Gas Town is ideally more of "Tell me what you want, I will spin up a graph of nodes that you can have some input on to complete your work".
i made a clone of beads in rust that uses CRDTs for real time sync to coordinate a bunch of coding agents at the same time! if running locally, it's instant, for git it takes around .6s after your last action. lives entirely in git, and is like... an actual distributed database/issue system, just works, and u never gotta think about it.
think about how this thing is interacting with your codebase. it can read one file at a time. sections of files.
in this UX, is it ergonomic to go hunting for patterns and conventions? if u have to linearly process every single thing u look at every time you do something, how are you supposed to have “peripheral vision”? if you have amnesia, how do you continue to do good work in a codebase given you’re a skilled engineer?
it is different from you. that is OK. it doesn’t mean its stupid. it means it needs different accomodations to perform as well as you do. accomodations IRL exist for a reason, different people work differently and have different strengths and weaknesses. just like humans, you get the most out of them if you meet and work with them from where they’re at.
Got it. But you could just use it on your MacBook on those occasions where you want to "talk" to your computer remotely to check on some progress it made on a specific job. My use case would involve switching desktops, activating specific windows, and reading their content and taking some action. But depends more specifically on the MCP that exposes that functionality, and not your app. I was asking because you're probably more familiar on how reliable such an approach might be.
heya, building this. been used in prod for a month now, has saved my customer’s ass while building general workflow automation agents. happy to chat if ur interested.
I don’t think you can get the same satisfaction out of these tools if what you want to do is not novel.
If you are exploring the space of possibilities for which there are no clear solutions, then you have to think hard. Take on wildly more ambitious projects. Try to do something you don’t think you can do. And work with them to get there.
reply