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

Launch HN: Twill.ai (YC S25) – Delegate to cloud agents, get back PRs

twill.ai

Post reply on HN
Print view View original

21–30 of 113 posts

Re: Launch HN: Twill.ai (YC S25) – Delegate to cloud agents, get back PRs

#21

Post by willydouhard »

dennisy wrote: post #20

Congrats on the launch, the agentbox-sdk looks interesting, but seeing as the first commit was 3 days ago - I feel a little wary to use it just yet! One question, do you have plans for any other forms of sandboxing that are a little more "lightweight"? Also how do you add more agent types, do you support just ACP?

Thank you! agentbox-sdk is very recent so it is not stable just yet indeed!

For the lightweight sandbox, can you give an example?

Currently we support main coding CLIs, ACP support is not shipped yet.

Re: Launch HN: Twill.ai (YC S25) – Delegate to cloud agents, get back PRs

#24

Post by danoandco »

2001zhaozhao wrote: post #17
danoandco wrote: post #11

Earlier quoted context omitted.

For a solo dev running one task at a time, a beefy desktop overnight is totally viable. We see a lot of this with the Mac Mini hype Cloud starts to matter when you want to (a) run a swarm of agents on multiple independent tasks in parallel, (b) share agents across a team, or (c) not worry about keeping a machine online

I would point out that a beefy desktop is probably faster at compiling code than a typical cloud instance simply due to more CPU performance. So maybe up to 10-ish concurrent agents it's faster to use a local desktop than a cloud instance, and then you start to get into the territory where multiple agents are compiling code at the same time, and the cloud setup starts to win. (That's assuming the codebase takes a whi…

Totally right on the compile time. CIs have the same bottleneck, and the ecosystem is working on fixing this (faster cpus, better caching) in both coding agents and CI to improve overall velocity

Re: Launch HN: Twill.ai (YC S25) – Delegate to cloud agents, get back PRs

#25

Post by willydouhard »

a_t48 wrote: post #22

Does it support running Docker images inside the sandbox?

Yes, for instance Twill is running a local postgres and redis directly in the sandbox using docker compose when running on our codebase.

This is what enables Twill to self verify its work before opening a PR

Re: Launch HN: Twill.ai (YC S25) – Delegate to cloud agents, get back PRs

#26

Post by 2001zhaozhao »

piker wrote: post #18
2001zhaozhao wrote: post #8

24/7 running coding agents are pretty clearly the direction the industry is going now. I think we'll need either on-premises or cloud solutions, since obviously if you need an agent to run 24/7 then it can't live on your laptop. Obviously cloud is better for making money, and some kind of VPC or local cloud solution is best for enterprise, but perhaps for individual devs, a self-hosted system on a home desktop comput…

> 24/7 running coding agents are pretty clearly the direction the industry is going now. This assertion needs some support for those of us that don't have a macro insight into the industry. Are you seeing this from within FAANG shops? As a solo developer? What? Honest question.

I'm speaking from my daily experience. Sometimes i don't want to close my laptop before going to bed because there are still 1-2 tasks ongoing in my AI kanban board, so I just leave my laptop open (lock but not suspend it) so that the agents keep working for a while. I don't even have things all that automated.

I anticipate that once I have some more complex agentic scaffolds set up to do things like automatically explore promising directions for the project, then leaving the AI system on overnight becomes a necessity.

Re: Launch HN: Twill.ai (YC S25) – Delegate to cloud agents, get back PRs

#27

Post by danoandco »

telivity-real wrote: post #23

[flagged]

We’re focused on SWE use cases. Code is nice because there’s already a built-in verification loop: diffs, tests, CI, review, rollback. But you do quickly get to a state where the agent needs to make a risky action (db migration, or an infra operation). And this is where the permissions features from the agents are handy: allowlist, automode, etc. So you have approve/reject only the high risk actions. And I think this risk model is valid for both technical and non-technical use cases

Re: Launch HN: Twill.ai (YC S25) – Delegate to cloud agents, get back PRs

#29

Post by danoandco »

senordevnyc wrote: post #28

How does this compare to something like Cursor Cloud Agents with a solid set of skills and tools?

Similar but reusing lab-native CLIs like Claude Code or Codex, which they perform RL on. And so in the long-run, we believe this approach wins over custom harnesses.
Post reply on HN