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

11–20 of 113 posts

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

#11

Post by danoandco »

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…

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

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

#12

Post by hmokiguess »

danoandco wrote: post #6
hmokiguess wrote: post #3

> Run the same agent n times to increase success rate. Are there benchmarks out there that back this claim?

Yes, this is the pass@k metric from code generation research. Found the relevant paper Evaluating Large Language Models Trained on Code (Chen et al., 2021) which introduced the metric.

Interesting, and how does Twill uses it in that feature?

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

#13

Post by willydouhard »

gbnwl wrote: post #10

So instead of using my Claude Code subscription, I can pay the vastly higher API rates to you so you can run Claude Code for me?

Anthropic recently killed the ability for third parties to use the Claude Code subscription, and it's assumed they're subsidising that price heavily. Which is fine, but it's a good reminder of the vendor lock-in risk. One policy change and your workflow breaks. Twill is agent-agnostic (Claude Code, Codex CLI, OpenCode), so you're not betting on any single vendor's pricing decisions.

On the cost for solo devs, yeah, if you're one person running one agent at a time on your laptop, the sub is probably the better deal today. No argument there. The cloud agent model starts to make sense when you want to fire off multiple tasks in parallel.

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

#14

Post by gbnwl »

willydouhard wrote: post #13
gbnwl wrote: post #10

So instead of using my Claude Code subscription, I can pay the vastly higher API rates to you so you can run Claude Code for me?

Anthropic recently killed the ability for third parties to use the Claude Code subscription, and it's assumed they're subsidising that price heavily. Which is fine, but it's a good reminder of the vendor lock-in risk. One policy change and your workflow breaks. Twill is agent-agnostic (Claude Code, Codex CLI, OpenCode), so you're not betting on any single vendor's pricing decisions. On the cost for solo devs, yeah, i…

Not sure if you've seen it yourself but Claude code can kick off parallel agents working in their own worktrees natively now. I do it all the time.

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

#16

Post by willydouhard »

gbnwl wrote: post #14
willydouhard wrote: post #13

Earlier quoted context omitted.

Anthropic recently killed the ability for third parties to use the Claude Code subscription, and it's assumed they're subsidising that price heavily. Which is fine, but it's a good reminder of the vendor lock-in risk. One policy change and your workflow breaks. Twill is agent-agnostic (Claude Code, Codex CLI, OpenCode), so you're not betting on any single vendor's pricing decisions. On the cost for solo devs, yeah, i…

Not sure if you've seen it yourself but Claude code can kick off parallel agents working in their own worktrees natively now. I do it all the time.

Yes, the difference is that Twill launches dedicated infra on each sandbox for each task. This means you can work on multiple tasks requiring a DB migration for instance.

Also you can fire and forget tasks (my favorite) and don't have to keep your laptop running at night.

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

#17

Post by 2001zhaozhao »

danoandco wrote: post #11
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…

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 while to compile and pegs your CPU at 100% while doing so. If the codebase is faster to compile or uses fewer threads, then the breakeven agent count is even higher.)

Other than that, I agree with what you said. I don't know what the tradeoffs for local on-premises and cloud agents are in terms of other areas like convenience, but I do think that scalability in the cloud is a big advantage.

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

#18

Post by piker »

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.

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

#19

Post by danoandco »

hmokiguess wrote: post #12
danoandco wrote: post #6

Earlier quoted context omitted.

Yes, this is the pass@k metric from code generation research. Found the relevant paper Evaluating Large Language Models Trained on Code (Chen et al., 2021) which introduced the metric.

Interesting, and how does Twill uses it in that feature?

[dead]

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

#20

Post by dennisy »

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?

Post reply on HN