Add llm-sandbox to Sandboxing & Isolation - #19
Open
vndee wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
llm-sandbox is an MIT-licensed Python library for running LLM-generated code in containers, with Docker, Podman and Kubernetes backends.
Relevant to this list's scope: it exposes per-session network isolation (including
none), read-only root filesystems, capability dropping, and CPU/memory limits, and provides a configurable static screen for code patterns before execution.I've described the static screen as advisory rather than enforcing, because that is what it is —
is_safe()returns a verdict and the caller decides;run()does not reject on its behalf. The entry also states plainly that this is container isolation with no kernel-level guarantees, which seemed more useful to readers of this list than claiming otherwise.Appended to the Sandboxing & Isolation table. I did not add the 🔥 marker, since that looks like a curation signal for you rather than something to self-apply.