Very cool. Just fyi, the GitHub links to some of the docs (like self-hosting) give 404, as do some of the internal links in the docs.
Launch HN: Runtime (YC P26) – Sandboxed coding agents for everyone on a team
41–48 of 48 posts
Re: Launch HN: Runtime (YC P26) – Sandboxed coding agents for everyone on a team
#42Congrats, amazing product!! How are guardrails set in a sandbox? Once I create my setup, is there a way to customize it per team? For example: I want to setup a different setup for my marketing vs my data team.
Re: Launch HN: Runtime (YC P26) – Sandboxed coding agents for everyone on a team
#43Tonka seems better equipped and free…
Re: Launch HN: Runtime (YC P26) – Sandboxed coding agents for everyone on a team
#44Your Video is stressing me out. Srlsy. Its too fast, its too jumpy
Re: Launch HN: Runtime (YC P26) – Sandboxed coding agents for everyone on a team
#45Re: Launch HN: Runtime (YC P26) – Sandboxed coding agents for everyone on a team
#46Interesting 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)?