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

41–50 of 113 posts

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

#41

Post by verdverm »

willydouhard wrote: post #39
verdverm wrote: post #35

Earlier quoted context omitted.

See also Cowork and other upcoming Anthropic features. See also Show HN, this exact product is frequently shown as a github link. The paradigm shift in Ai means what you are making is (1) filling a gap until the primaries implement it, most have it in their pipeline if not already (2) how easy it is to replicate with said Ai using my preferred tech stack

Cowork does not seem to be focused on engineering, but we are fully expecting Anthropic to catch up in this category. What Anthropic can't offer is to let you use Codex or combine it with Claude Code. That is why we think non ai-labs players have a say in this market. To your last point, as always there is a buy vs build tradeoff which ultimately comes down to focusing on your core business which we think still remai…

> as always there is a buy vs build tradeoff

it's a nonbinary decision now

Google has a free, open source take on what you are building, looks more mature as well

https://googlecloudplatform.github.io/scion/overview/

My comment about Cowork is more about pointing out a different feature set that will crossover with Code. In example they have the Task related things as an affordance, Code has this coming.

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

#42

Post by auszeph »

willydouhard wrote: post #36
auszeph wrote: post #33

I built an internal version of this for my workplace. Something very useful that will be harder for you most likely is code search. Having a proper index over hundreds of code repos so the agent can find where code is called from or work out what the user means when they use an acronym or slightly incorrect name. It's quite nice to use and I'm sure someone will make a strong commercial offering. Good luck

I agree and that is why I think monorepos are making a comeback. That said, there are workarounds, like cloning all repos and enabling LSP (coding CLIs added that feature) or using a dedicated solution for codebase indexing and add a skill/mcp. Super fast models spamming grep commands are also fun to watch! Curious to know how you implemented it in house.

https://github.com/sourcegraph/zoekt

Run a copy of this in the same VPC. Monorepos would definitely help, but that's not the structure we have. I didn't want to rely on API limits (or stability) at GitHub for such a core feature.

Using this we've had agents find dead APIs across multiple repos that can be cleaned up and the like. Very useful.

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

#44

Post by willydouhard »

verdverm wrote: post #41
willydouhard wrote: post #39

Earlier quoted context omitted.

Cowork does not seem to be focused on engineering, but we are fully expecting Anthropic to catch up in this category. What Anthropic can't offer is to let you use Codex or combine it with Claude Code. That is why we think non ai-labs players have a say in this market. To your last point, as always there is a buy vs build tradeoff which ultimately comes down to focusing on your core business which we think still remai…

> as always there is a buy vs build tradeoff it's a nonbinary decision now Google has a free, open source take on what you are building, looks more mature as well https://googlecloudplatform.github.io/scion/overview/ My comment about Cowork is more about pointing out a different feature set that will crossover with Code. In example they have the Task related things as an affordance, Code has this coming.

I believe there is a difference between an open source framework and a product. You would still have to manage and scale your infra, build the integration layer around it to make it accessible where your teams are, fix bugs etc...

I am not saying that build is always the bad choice, but the tradeoff did not disappear imo

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

#45

Post by eranation »

Edit: just noticed this is a semi duplicate question to https://news.ycombinator.com/item?id=47723506 so rephrasing my question - will you have computer use and will you have self-hosted runners option? (you being just the controlplane / task orchestrator, which is the hardest problem apparently...)

Additional question - what types of sandboxes you use? (just docker or also firecracker etc...)

Original comment:

Congrats on the launch!

What's the benefit over cursor cloud agents with computer use? (other than preventing vendor lock in?)

https://cursor.com/blog/agent-computer-use

Or the existing Claude Code Web?

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

#46

Post by verdverm »

willydouhard wrote: post #44
verdverm wrote: post #41

Earlier quoted context omitted.

> as always there is a buy vs build tradeoff it's a nonbinary decision now Google has a free, open source take on what you are building, looks more mature as well https://googlecloudplatform.github.io/scion/overview/ My comment about Cowork is more about pointing out a different feature set that will crossover with Code. In example they have the Task related things as an affordance, Code has this coming.

I believe there is a difference between an open source framework and a product. You would still have to manage and scale your infra, build the integration layer around it to make it accessible where your teams are, fix bugs etc... I am not saying that build is always the bad choice, but the tradeoff did not disappear imo

[flagged]

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

#47

Post by willydouhard »

eranation wrote: post #45

Edit: just noticed this is a semi duplicate question to https://news.ycombinator.com/item?id=47723506 so rephrasing my question - will you have computer use and will you have self-hosted runners option? (you being just the controlplane / task orchestrator, which is the hardest problem apparently...) Additional question - what types of sandboxes you use? (just docker or also firecracker etc...) Original comment: Congr…

We already support computer use out of the box (linux sandboxes). Self hosted runners are not available yet, but Twill is built on a runtime agnostic layer (see https://github.com/TwillAI/agentbox-sdk) so it is feasible!

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

#49

Post by willydouhard »

eranation wrote: post #48

HN hug of death probably, but your scorecard returns an error :( The analysis request failed. Hosted shell completed without parseable score_repo.py JSON output. 11 command(s), 11 output(s). (rest redacted)

Thank you for the feedback, we are working on it!

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

#50

Post by eranation »

willydouhard wrote: post #47
eranation wrote: post #45

Edit: just noticed this is a semi duplicate question to https://news.ycombinator.com/item?id=47723506 so rephrasing my question - will you have computer use and will you have self-hosted runners option? (you being just the controlplane / task orchestrator, which is the hardest problem apparently...) Additional question - what types of sandboxes you use? (just docker or also firecracker etc...) Original comment: Congr…

We already support computer use out of the box (linux sandboxes). Self hosted runners are not available yet, but Twill is built on a runtime agnostic layer (see https://github.com/TwillAI/agentbox-sdk ) so it is feasible!

You definitely got my interest... will try it out!
Post reply on HN