Live data from Hacker News

Launch HN: Runtime (YC P26) – Sandboxed coding agents for everyone on a team

runtm.com

21–30 of 48 posts

Re: Launch HN: Runtime (YC P26) – Sandboxed coding agents for everyone on a team

#21

Checked license it said copyrighted which makes this unsuable for me. my question is what advantage does this have over real FOSS agentic sandboxes

I wrote a simpler version of this for Claude Code as open source if that's useful to you: https://github.com/smithy-ai/smithy-ai

It's doing context management in the same way, but adds a learning loop based on code reviews. Currently works with Gitlab, Forgejo and Gitea but happy to accept a PR for Github support or co-write it.

Re: Launch HN: Runtime (YC P26) – Sandboxed coding agents for everyone on a team

#23

Really cool! We're working on something similar over at https://norisessions.com/ A few questions - you mention proxying keys. One issue that we run into is that there are a bunch of tools that are really useful but require keys to be on disk (e.g. aws cli -- yes yes you can do IAM permissions but still). How do you guys think about those? (Especially since your setup onboarding is 'just install from npm or mise') -…

Nori looks really cool, will set up sometime to exchange notes. But with regards to your questions: - Proxying keys: We allow users to setup keys in the sandbox and use CLIs for some cases but we also support an egress gateway that intercepts and injects keys on the way out, which supports the major api integrations we offer. - We still allow fly.io for deployments (so after a sandbox has a final app, you can deploy…

we're on fly, going to add modal support soon. I dont think our users care all that much, but we care for dev ergonomics.

keys are tricky. We don't have a great answer. I mean the proxy inject works well enough for mcp, but there is just such a long tail of tools that do something like 'read a key from disk and encrypt it before sending it out' which makes proxy management just a pain

Re: Launch HN: Runtime (YC P26) – Sandboxed coding agents for everyone on a team

#25
Interesting approach to sandboxing. One thing I've been thinking about in this space: even with sandboxed execution, the generated code still needs to pass security policy checks before it merges. Static analysis catches a different class of issues than runtime sandboxing — they seem complementary rather than competing.

Re: Launch HN: Runtime (YC P26) – Sandboxed coding agents for everyone on a team

#26

Congrats on the launch! Tiny bit of feedback on the demo video: the beginning makes me dizzy and I'm not sure what's going on (was watching on my phone).

Thanks! The demo is not the best we have. Probably did a lot of zooming in and zooming out.

Re: Launch HN: Runtime (YC P26) – Sandboxed coding agents for everyone on a team

#27
post #25

Interesting approach to sandboxing. One thing I've been thinking about in this space: even with sandboxed execution, the generated code still needs to pass security policy checks before it merges. Static analysis catches a different class of issues than runtime sandboxing — they seem complementary rather than competing.

I agree, I do see static analysis and runtime sandbox as complementary tools. Do you see static analysis tools performed by the agent itself inside the sandbox or via CI tools in the pull request itself (like github actions or buildkite)?
Post reply on HN