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

101–110 of 113 posts

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

#101

Post by rachel_rig »

mike_hearn wrote: post #98
hardsnow wrote: post #4

I’ve been developing an open-source version of something similar[1] and used it quite extensively (well over 1k PRs)[2]. I’m definitely believer of the “prompt to PR model”. Very liberating to not have to think about managing the agent sessions. Seems that you have built a lot of useful tooling (e.g., session videos) around this core idea. Couple of learnings to share that I hope could be of use: 1) Execution sandbox…

Very cool. I've been putting together something very similar, although mine only does email and not Slack. Also it uses Codex not Claude Code, and just relies on ordinary UNIX user isolation rather than containers that are created/destroyed for every request. I just issue it with restricted API keys and rely on the fact that most products already allow humans to be 'sandboxed' via ordinary permissions. I've also (sep…

[flagged]

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

#103

Post by dbbk »

willydouhard wrote: post #91
blacksoil wrote: post #83

Claude code has a version that runs on the cloud. You grant it access to Github then and you can tell it to make changes and create PR from your phone, tablet, or desktop. I'm curious, but what makes this difference than that?

The main difference is that you can pick/combine coding agent CLIs (claude code, codex, open code). There is no vendor lock-in.

That's literally just GitHub agents?

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

#104

Post by dbbk »

willydouhard wrote: post #16
gbnwl wrote: post #14

Earlier quoted context omitted.

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.

Claude literally does this

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

#105

Post by contraposit »

dbbk wrote: post #102

There are billions of these. What's different?

Another question is would a future world require so much code that we turn code generation into a service itself. Perhaps an analogy will help. e.g. do we use our lawnmowers 24x7? I understand we will have far more code in future but current capacity (devs working on code on laptops) should be sufficient.

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

#106

Post by danoandco »

dbbk wrote: post #103
willydouhard wrote: post #91

Earlier quoted context omitted.

The main difference is that you can pick/combine coding agent CLIs (claude code, codex, open code). There is no vendor lock-in.

That's literally just GitHub agents?

Yes, broadly. The main structural difference is that we’re agent-agnostic, so we can combine lab-native CLIs in one workflow. GitHub will likely struggle there because they have direct partnerships with Anthropic and OpenAI.

On the features themselves, we have a better UX across integrations, and more advanced features like video recording.

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

#108

Post by danoandco »

glompylabs wrote: post #99

Running agents on a home server (Claude Code via systemd timers, not cloud sandboxes) has been interesting. Over 700+ autonomous sessions so far. The biggest practical difference from cloud solutions: agents that run on your own machine can interact with your actual environment. Our agents browse the web, manage a Discord bot, push to git repos, and read email. They share a filesystem so one agent's output is another…

Definitely and Twill is for SWE delegation first, not so much the “general agent on my machine.”

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

#109

Post by willydouhard »

dennisy wrote: post #96
willydouhard wrote: post #21

Earlier quoted context omitted.

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.

I was thinking something that runs in the same process, and does not require docker or a third party API. For example Monty by the pydantic team, or the Anthropic sandbox which I believe uses OS level primitives.

Got it! Yes this is definitely doable, added in the roadmap. We will embed the roadmap in the readme soon.

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

#110

Post by dbbk »

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've just set up an old MacBook with tmux and ssh/mosh, you can run as many parallel Claudes in the 'cloud' as you want
Post reply on HN