[HN Gopher] Show HN: Remoroo. trying to fix memory in long-runni...
___________________________________________________________________
Show HN: Remoroo. trying to fix memory in long-running coding
agents
I built Remoroo because most coding agents fall apart once the work
stops being a short edit-and-run loop. A real engineering
experiment can run for hours. Along the way, the agent reads files,
runs commands, checks logs, compares metrics, tries ideas that
fail, and needs to remember what already happened. Once context
starts slipping, it forgets the goal, loses track of the baseline,
and retries bad ideas. Remoroo is my attempt to solve that
problem. You point it at a repo and give it a measurable goal. It
runs locally, tries changes, executes experiments, measures the
result, keeps what helps, and throws away what does not. A big
part of the system is memory. Long runs generate far more context
than a model can hold, so I built a demand-paging memory system
inspired by OS virtual memory to keep the run coherent over time.
There is a technical writeup here:
https://www.remoroo.com/blog/how-remoroo-works Would love feedback
from people working on long-running agents, training loops, eval
harnesses, or similar workflows.
Author : adhamghazali
Score : 22 points
Date : 2026-04-14 13:51 UTC (4 days ago)
(HTM) web link (www.remoroo.com)
(TXT) w3m dump (www.remoroo.com)
| poszlem wrote:
| I have no comments on the product and wish you all the best with
| it, but the AI copy on the page is so painful to read.
|
| "Not a coding agent. An autonomous research engine."
|
| "It didn't guess. It proved."
|
| "> 30 experiments completed > 8 kept * 22 discarded > val_bpb:
| 2.24 - 1.55 > VERIFIED * REPRODUCIBLE You slept through it."
| holoduke wrote:
| I am doing something similar with
| https://github.com/holoduke/myagent This project is actually some
| autonomous system that reads papers and tries to implement them.
| A fun experiment I would say.
| eventualcomp wrote:
| > Would love feedback from people working on long-running agents,
| training loops, eval harnesses, or similar workflows.
|
| I have not required a service for this kind of optimization at
| work. Though work gives me unbounded access to Claude 4.x-1m
| (substitute x with whatever is available). So I often ask it to
| do this kind of task.
|
| I found that when I just specify, sometimes the AI will optimize
| to the point that it breaks other existing functional
| requirements in the same codebase. So I have to steer it with
| invariants. This is where the bulk of my effort is - monitoring
| to make sure that the agent didn't suddenly scramble the infra or
| delete valid usecases.
|
| 1. How do you address that [paperclip
| problem](https://en.wikipedia.org/wiki/Instrumental_convergence)
| in Remoroo? Can we define invariants? 2. Why is there a whole
| orchestration system? Was there some limitation that prompted
| this architecture, e.g. did workers die frequently? Looks like
| Temporal/AWS SWF with the brain/worker/control architecture. The
| existence of `q (quit): Kills the Worker, aborts the run. The run
| is marked FAILED.` makes me think there's only one worker...so
| why...? It'd make more sense if the brain wanted to dispatch
| multiple hypotheses to multiple workers to test in parallel (e.g.
| if optimizing SQL, try these different joins all at once, discard
| queries running for X minutes after the first complete one).
___________________________________________________________________
(page generated 2026-04-18 23:00 UTC)