Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI agent developers, security-conscious engineering teams, regulated industries, and platform teams who need a local credential control that keeps raw credentials out of AI coding agent context and tool output without changing the agent's workflow. The durable differentiator is the typed-handle + local-approval + sanitized-output + audit-log combination — the right shape for any AI agen
Who should use it
Who should skip it
Pass on sgateway/s-gw if its scope or audience does not match what your team is building right now.
About this signal
sgateway/s-gw is tracked by RepoRadar as a local credential control for ai in the AI Agent Security section. It was first seen on 2026-07-04 and last updated on 2026-07-04. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. The standout signals for sgateway/s-gw are workflow potential (9.5) and novelty (9.0), while momentum (6.0) trails — that balance shapes where it fits best. This page summarizes the evidence RepoRadar has captured from captured source metadata. 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 sgateway/s-gw a composite score of 8.0 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 1.0 and never affects the composite score or tier. The risk label of 'conditional' 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
Project is in preview (status=preview) — storage formats and interfaces may change; pin to a specific commit if stability matters for the credential control surface; Windows support is experimental — the macOS app + menu helper + Keychain integration is the production path; Windows Credential Manager is supported but the menu helper and operator UI are macOS-first.