Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for teams that want coding agents to run in real sandboxes rather than on a developer laptop. It makes the remote-control layer reusable, which is a much more practical step toward safe agent execution than another local-only wrapper.
Who should use it
Who should skip it
Skip rivet-dev/sandbox-agent if you cannot isolate its execution environment or audit what data it touches before connecting anything sensitive.
About this signal
rivet-dev/sandbox-agent is tracked by RepoRadar as a framework in the Radar section. It was first seen on 2026-06-19 and last updated on 2026-06-19. The current verdict is 'try now' with a Gold tier and advanced setup difficulty. rivet-dev/sandbox-agent leads on workflow potential (10.0) and practical usefulness (9.0); its lowest signal is setup ease (4.2), so factor that in before investing setup time. This page summarizes the public evidence on the linked source page and states where additional review is still needed. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned rivet-dev/sandbox-agent a composite score of 9.0 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 88.0 and never affects the composite score or tier. The risk label of 'medium' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
This framework is designed to run real coding agents that can execute code and touch repositories inside a sandbox, so start with isolated environments and low-privilege credentials until you trust the permission flow.