Viewing profile — BenceRed

Re: the dev box, it works very well for individuals and small sized teams, but starts to become an operational burden past a certain size. Our ideal customer is one who has a ton o…

We're going to be investing pretty heavily in evals/benchmarks over the next couple of weeks, so that should give us a much better understanding of how our custom harness stacks up…

We use 'phalanx' internally!

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 s…

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…

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…

Agreed, we're working with a designer and are going to be fixing this very soon. Our main focus has been on making sure the product itself looks and feels very good to use -- proba…

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 …

Yes, agents have a persistent Chromium session they use via the agent-browser CLI. Typical workflow would involve starting the preview, seeding data, then the agent going through t…

exe.dev works quite well for giving an agent a computer and managing it remotely, but seems to require a fair bit more configuration to achieve parity with what we offer out of the…

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 wan…

That setup is pretty much what we're trying to offer with Hoplite! Using us means losing freedom and control with regards to infrastructure, however we think that's a tradeoff peop…

Modal just released some features that would allow users to bring custom Docker images, and I'm working on getting your exact use case supported! Aiming to get it out by the end of…

This one: https://www.daytona.io . Their platform was OSS for a long time but they decided to go closed source recently.

You can do either. If you don't want to migrate over fully, I'd recommend setting up an automation to fix Sentry/PostHog issues as they come in. You can get a good feel for the pla…

Modal has a lot of small niceties that made them easy to implement, such as filesystem snapshots and programmatic build images. But I did see that AWS recently launched Lambda Micr…

Agreed. Per-thread VMs are quite similar to how local agents use worktrees to avoid cross contamination, but with the added benefit of being able to easily scale up/down compute re…

Agreed 100%. We've been working with a designer on a complete redesign of our landing page to avoid that vibey-smell.

At the moment we're using Daytona as a redundant fallback in case Modal experiences an outage, but they have very stringent limits on how many resources we can consume concurrently…

Thank you! Regarding models, as you said we're not locked into a specific provider, and are able to offer open weight models like Kimi K3 and GLM 5.2 Our pricing is higher than oth…

Yeah, luckily they're in quite a different domain to us -- hopefully shouldn't have too much trouble winning the SEO battle

Hi HN, we’re Bence and Ryan, founders of Hoplite ( https://hoplite.sh ). Hoplite lets you deploy coding agents in the cloud, with a suite of tools that makes it incredibly easy to …