Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Hoplite (YC S26) – Effortlessly deploy cloud coding agents

hoplite.sh

Post reply on HN
Print view View original

41–50 of 73 posts

Re: Launch HN: Hoplite (YC S26) – Effortlessly deploy cloud coding agents

#41

Post by BenceRed »

asdev wrote: post #39
BenceRed wrote: post #37

Earlier quoted context omitted.

Agreed that at the moment it's a very difficult problem, but one we're looking to solve! I think it becomes a no-brainer for most people if we're able to give each agent a replica of their production stack. What does your current setup look like? And are you using an open source solution like OpenInspect for your in-house version, or building it from the ground up?

Building from ground up using OpenAI Agents SDK. We already have custom in house Cloud Development Environment, so the effort is just to "agent-ize" though which is not small. That's why I feel any team with any sort of infra support likely won't buy your product, since they already have the tribal knowledge to set this up. Newer teams might. But overall porting people's dev envs into the cloud is a tarpit problem(IM…

I think for use cases like that, we'd offer on-prem deployments (similar to Factory), potentially coupled with a FDE. Still need to do a lot more research into the enterprise space.

Re: Launch HN: Hoplite (YC S26) – Effortlessly deploy cloud coding agents

#42

Post by xander_north »

Really interesting. I've been working on building out more self-sufficient agents with harnesses to match, and this feels like the next logical step. I'd love to try this.

Curious how you guys are thinking about the difference between project-specific and project-agnostic harnesses and tooling. For me, it feels like a lot of the work is project specific and I'm not sure how to abstract that.

P.S. The code is not working for me.

Re: Launch HN: Hoplite (YC S26) – Effortlessly deploy cloud coding agents

#43

Post by BenceRed »

kristianc wrote: post #40

>> It opens a pull request >> Then keeps iterating as review comments land, in the same thread, with the same context. My experience, particularly with Sol is that agents are generally really bad at knowing when to stop 'iterating' and will continue covering off ever-more obscure edge cases. How does Hoplite solve for this?

We've observed this pattern as well, and have counteracted it by keeping the tasks very finely scoped. For example, "The test(api) check has failed. Fix it, then immediately commit and push." -- or -- "The following comments have been added by reviewers. Resolve each one, then immediately commit and push."

This specificity helps Sol stay on track (most of the time). It doesn't work as well when the comment questions a complex piece of the architecture though.

Re: Launch HN: Hoplite (YC S26) – Effortlessly deploy cloud coding agents

#44

Post by BenceRed »

xander_north wrote: post #42

Really interesting. I've been working on building out more self-sufficient agents with harnesses to match, and this feels like the next logical step. I'd love to try this. Curious how you guys are thinking about the difference between project-specific and project-agnostic harnesses and tooling. For me, it feels like a lot of the work is project specific and I'm not sure how to abstract that. P.S. The code is not work…

In general, we've found that over the past couple of years agent harnesses have gotten much less restrictive, allowing the agent freedom to choose its own way of doing things. It seems like the project agnostic vs. specific harnesses will follow that trend. The pattern will work well for the current gen models, but eventually Fable 7 will be able to intuit how it should approach a specific project very well, at which point the challenge is making sure it has the tools to do so.

And I've made some changes to the coupon, does it work now?

Re: Launch HN: Hoplite (YC S26) – Effortlessly deploy cloud coding agents

#45

Post by Bnjoroge »

BenceRed wrote: post #31
Bnjoroge wrote: post #30

What’s the experience like going from an active on-going thread to a cloud-hosted one? I dont wanna always work on the cloud, and want my current setup to be exactly the same as in the cloud, and should be pretty seamless. Only folks i’ve seen solve these are folks who run the sandboxes locally and take that to the cloud like smolvm/microsandbox.

This is still something we're working on making seamless. The current approach is to install our MCP server and ask the local agent to start up a new thread on Hoplite when you want to transition to the cloud, but it doesn't carry over file system changes. (Unless you first push the contents to a remote branch, at which point the Hoplite agent can pull it down.)

gotcha. yea ideally you take a full live snapshot of my current state, untracked files, processes etc, and resume them in the cloud. Congrats on the launch! A mobile app would also be nice

Re: Launch HN: Hoplite (YC S26) – Effortlessly deploy cloud coding agents

#48

Post by xander_north »

BenceRed wrote: post #44
xander_north wrote: post #42

Really interesting. I've been working on building out more self-sufficient agents with harnesses to match, and this feels like the next logical step. I'd love to try this. Curious how you guys are thinking about the difference between project-specific and project-agnostic harnesses and tooling. For me, it feels like a lot of the work is project specific and I'm not sure how to abstract that. P.S. The code is not work…

In general, we've found that over the past couple of years agent harnesses have gotten much less restrictive, allowing the agent freedom to choose its own way of doing things. It seems like the project agnostic vs. specific harnesses will follow that trend. The pattern will work well for the current gen models, but eventually Fable 7 will be able to intuit how it should approach a specific project very well, at which…

It does, thanks! Looking forward to trying this out.

Re: Launch HN: Hoplite (YC S26) – Effortlessly deploy cloud coding agents

#49

Post by yoanwaidev »

r5Khe wrote: post #10

Looks neat! I've been using Amp ( https://ampcode.com/ ) for a while (Which seems to be doing something very similar), and I really appreciate this type of workflow. One thread = one VM feels like a solid model going forward.

Same instinct locally with git worktrees: one agent per worktree so they do not thrash the same checkout. Cloud VMs buy isolation and scale; worktrees buy cheap isolation when you already have a machine. I end up using both patterns depending on whether the bottleneck is compute or just not stepping on each other.
Post reply on HN