Item detail
github.com

rivet-dev/sandbox-agent

rivet-dev/sandbox-agent is a framework in RepoRadar's Radar section, holding Gold tier and a 'try now' verdict. Its strongest signal is workflow potential, scored 10.0 out of 10.

Score9.0
Popularity88.0
Riskmedium
TierGold
Score breakdown
Usefulness9.0
Novelty8.0
Momentum9.0
Maturity8.8
Open-source/build8.4
Evidence7.2
Workflow potential10.0
Setup ease4.2

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

platform teams AI coding-agent builders developer infrastructure engineers teams that want isolated agent execution

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.

Evidence links
Closest alternatives / related signals
coding-agents sandbox remote-execution http-api developer-infrastructure
Verification record

What RepoRadar actually verified

Discovered

Automated discovery and source capture. Last checked 2026-08-03T18:56:10Z.

No editorial or hands-on review is claimed. This record remains at Discovered.

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

36 dated snapshots retained from 2026-06-19 through 2026-08-03; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score9.0 current · +0.0 net
Repository momentum5.8 current · -3.2 net
GitHub stars (observed)1,515 current · +36 net
GitHub stars1,515 exact observation
Versionv0.5.0-rc.3
Last release2026-03-30T18:53:54Z
Maintenancemaintained
Current riskmedium
Current verdicttry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineClaude, Claude Code, OpenAI Codex

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-08-039.05.81,515mediumtry nowmaintained
2026-08-029.05.51,512mediumtry nowmaintained
2026-08-019.05.51,511mediumtry nowmaintained
2026-07-319.09.0Not recordedmediumtry nownot recorded
2026-07-309.09.0Not recordedmediumtry nownot recorded
2026-07-299.05.81,507mediumtry nowmaintained
2026-07-289.05.51,503mediumtry nowmaintained
2026-07-219.07.51,486mediumtry nowactive
2026-07-209.07.51,486mediumtry nowactive
2026-07-199.07.51,486mediumtry nowactive
2026-07-189.07.51,486mediumtry nowactive
2026-07-179.07.51,486mediumtry nowactive

Why the record changed

stars changed

Stars changed: 1512 → 1515.

stars changed

Stars changed: 1511 → 1512.

stars changed

Stars changed: 1503 → 1507.

maintenance changed

Maintenance changed: active → maintained.

stars changed

Stars changed: 1486 → 1503.

stars changed

Stars changed: 1479 → 1486.