Live registry search

Results for “sandbox”

Exact name and slug matches are checked against the live registry before ranked alternatives.

Clear search

Decision filters

Choose by scenario, quality, and trust signals.

Use casePlatform fitQuality tierTrust profileSafety gateGitHub adoption

Showing 1-16 of 42 ranked candidates matching "sandbox"

Best blend of relevance, quality, freshness, and verified outcomes

OpenSandbox

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDCODING

Secure, Fast, and Extensible Sandbox runtime for AI agents.

$ npx skills add alibaba/OpenSandbox

14.0K stars72 quality90 trustReviewed6d since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

CLI + Codex · 4 targets

pythonai-agents

by alibabaDetailsQuick view

Amazing Sandbox

PROMISING · 66TRUST · 76SAFE · REVIEWEDCODING

Amazing Sandbox - run third-party tools and AI agents securely on your machine

$ npx skills add ashishb/amazing-sandbox

130 stars46 quality76 trustReviewed with permission notes2mo since pushNeeds review

QualityUseful candidate, but compare it with alternatives before adopting.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

CLI + Codex · 4 targets

godevops

by ashishbDetailsQuick view

Windows Sandbox

NEEDS REVIEW · 48TRUST · 70SAFE · EXPERIMENTALCODING

Disposable, secure and lightweight Windows Desktop Environment

$ npx skills add microsoft/Windows-Sandbox

538 stars38 quality70 trustExperimental2y since pushNeeds review

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustPotentially useful, but at least one trust signal needs human inspection.Review: Repository looks stale

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

CLI + Codex · 4 targets

powershelldeveloper-tools

by microsoftDetailsQuick view

Sandbox Agent

VERIFIEDEXCELLENT · 91TRUST · 85SAFE · REVIEWEDCODING

Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

$ npx skills add rivet-dev/sandbox-agent

1.4K stars61 quality85 trustReviewedClaude Code + OpenAI Agents2mo since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustGood trust signals with a few areas worth checking before rollout.Review: Documentation summary is thin

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

Claude Code + OpenAI Agents · 4 targets

typescriptcoding-agent

by rivet-devDetailsQuick view

Rancher Desktop

VERIFIEDEXCELLENT · 98TRUST · 86SAFE · REVIEWEDCODING

Container Management and Kubernetes on the Desktop

$ npx skills add rancher-sandbox/rancher-desktop

7.2K stars66 quality86 trustReviewed2mo since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

CLI + Codex · 4 targets

typescriptkubernetes

by rancher-sandboxDetailsQuick view

Agent Safehouse

VERIFIEDEXCELLENT · 92TRUST · 82SAFE · REVIEWEDCODING

Sandbox your local AI agents so they can read/write only what they need

$ npx skills add eugene1g/agent-safehouse

1.9K stars62 quality82 trustReviewed with permission notesClaude Code1mo since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustGood trust signals with a few areas worth checking before rollout.Review: Documentation summary is thin

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

Claude Code + CLI · 4 targets

shellai-agents

by eugene1gDetailsQuick view

Secure Exec

STRONG · 75TRUST · 75SAFE · EXPERIMENTALCODING

Secure Node.js Execution Without a Sandbox A lightweight library for secure Node.js execution. No containers, no VMs — just npm-compatible sandboxing out of the box.

$ npx skills add rivet-dev/secure-exec

915 stars51 quality75 trustExperimental2mo since pushNeeds review

QualitySolid option that is likely worth shortlisting for production workflows.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

CLI + Codex · 4 targets

javascriptai-agents

by rivet-devDetailsQuick view

SmolVM

STRONG · 73TRUST · 79SAFE · REVIEWEDCODING

Open-source AI sandbox infrastructure with unified API for VMMs -- Firecracker, QEMU and libkrun.

$ npx skills add CelestoAI/SmolVM

614 stars50 quality79 trustReviewed with permission notesBrowser agents2mo since pushNeeds review

QualitySolid option that is likely worth shortlisting for production workflows.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Browser agents + CLI · 4 targets

pythoncomputer-use

by CelestoAIDetailsQuick view

K8e

STRONG · 72TRUST · 76SAFE · REVIEWEDCODING

k8e.sh - OpenSource Agentic AI Sandbox Matrix

$ npx skills add xiaods/k8e

453 stars49 quality76 trustReviewed with permission notes3mo since pushNeeds review

QualitySolid option that is likely worth shortlisting for production workflows.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

CLI + Codex · 4 targets

gokubernetes

by xiaodsDetailsQuick view

Open Design

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · VERIFIEDDESIGN

🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · ima…

$ npx skills add nexu-io/open-design

88.1K stars78 quality91 trustVerifiedClaude Code + OpenAI Agents6d since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…

Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Design and creative · I need my agent to produce design assets, UI directions, presentations, or creative media workflows.

Claude Code + OpenAI Agents · 4 targets

typescriptai-agents

by nexu-ioDetailsQuick view

Lisa

NEEDS REVIEW · 47TRUST · 69SAFE · EXPERIMENTALRESEARCH

Sandbox for automated Linux malware analysis.

$ npx skills add danielpoliakov/lisa

486 stars38 quality69 trustExperimental3y since pushNeeds review

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustPotentially useful, but at least one trust signal needs human inspection.Review: Repository looks stale

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Research agents · I need my agent to research a topic, compare sources, and produce a concise report.

CLI + Codex · 4 targets

pythoniot

by danielpoliakovDetailsQuick view

Deer Flow

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDRESEARCH

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it…

$ npx skills add bytedance/deer-flow

71.1K stars74 quality90 trustReviewedClaude Code2mo since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Research agents · I need my agent to research a topic, compare sources, and produce a concise report.

Claude Code + CLI · 4 targets

pythonmulti-agent

by bytedanceDetailsQuick view

Cua

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDRESEARCH

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows…

$ npx skills add trycua/cua

21.4K stars74 quality91 trustReviewed8d since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Research agents · I need my agent to research a topic, compare sources, and produce a concise report.

CLI + Codex · 4 targets

htmlcomputer-use

by trycuaDetailsQuick view

Pi Less Yolo

PROMISING · 66TRUST · 72SAFE · EXPERIMENTALCODING

Slightly less YOLO version of pi-coding-agent in Docker container sandbox

$ npx skills add cjermain/pi-less-yolo

120 stars45 quality72 trustExperimental2mo since pushNeeds review

QualityUseful candidate, but compare it with alternatives before adopting.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

CLI + Codex · 4 targets

shellcoding-agent

by cjermainDetailsQuick view

Cultivar

PROMISING · 67TRUST · 75SAFE · EXPERIMENTALCODING

Use cultivar to test your Agent Skills, run them in sandboxes, and across different agents.

$ npx skills add pinecone-io/cultivar

37 stars45 quality75 trustExperimentalClaude Code13d since pushNeeds review

QualityUseful candidate, but compare it with alternatives before adopting.Check: Low GitHub adoption signal

TrustGood trust signals with a few areas worth checking before rollout.Review: Low GitHub adoption signal

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

Claude Code + CLI · 4 targets

python

by pinecone-ioDetailsQuick view

Flue

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

The sandbox agent framework.

$ npx skills add withastro/flue

7.5K stars69 quality88 trustReviewed30d since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

CLI + Codex · 4 targets

typescriptllm

by withastroDetailsQuick view

Page 1

Showing the strongest 16 results to keep the registry fast for humans and agents. Refine by use case, platform, stars, or search query for a narrower shortlist.

Try the agent resolve API

Live registry search

Results for “sandbox”

Exact name and slug matches are checked against the live registry before ranked alternatives.

Clear search

Decision filters

Choose by scenario, quality, and trust signals.

Use casePlatform fitQuality tierTrust profileSafety gateGitHub adoption

Showing 1-16 of 42 ranked candidates matching "sandbox"

Best blend of relevance, quality, freshness, and verified outcomes

OpenSandbox

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDCODING

Secure, Fast, and Extensible Sandbox runtime for AI agents.

$ npx skills add alibaba/OpenSandbox

14.0K stars72 quality90 trustReviewed6d since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

CLI + Codex · 4 targets

pythonai-agents

by alibabaDetailsQuick view

Amazing Sandbox

PROMISING · 66TRUST · 76SAFE · REVIEWEDCODING

Amazing Sandbox - run third-party tools and AI agents securely on your machine

$ npx skills add ashishb/amazing-sandbox

130 stars46 quality76 trustReviewed with permission notes2mo since pushNeeds review

QualityUseful candidate, but compare it with alternatives before adopting.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

CLI + Codex · 4 targets

godevops

by ashishbDetailsQuick view

Windows Sandbox

NEEDS REVIEW · 48TRUST · 70SAFE · EXPERIMENTALCODING

Disposable, secure and lightweight Windows Desktop Environment

$ npx skills add microsoft/Windows-Sandbox

538 stars38 quality70 trustExperimental2y since pushNeeds review

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustPotentially useful, but at least one trust signal needs human inspection.Review: Repository looks stale

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

CLI + Codex · 4 targets

powershelldeveloper-tools

by microsoftDetailsQuick view

Sandbox Agent

VERIFIEDEXCELLENT · 91TRUST · 85SAFE · REVIEWEDCODING

Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

$ npx skills add rivet-dev/sandbox-agent

1.4K stars61 quality85 trustReviewedClaude Code + OpenAI Agents2mo since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustGood trust signals with a few areas worth checking before rollout.Review: Documentation summary is thin

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

Claude Code + OpenAI Agents · 4 targets

typescriptcoding-agent

by rivet-devDetailsQuick view

Rancher Desktop

VERIFIEDEXCELLENT · 98TRUST · 86SAFE · REVIEWEDCODING

Container Management and Kubernetes on the Desktop

$ npx skills add rancher-sandbox/rancher-desktop

7.2K stars66 quality86 trustReviewed2mo since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

CLI + Codex · 4 targets

typescriptkubernetes

by rancher-sandboxDetailsQuick view

Agent Safehouse

VERIFIEDEXCELLENT · 92TRUST · 82SAFE · REVIEWEDCODING

Sandbox your local AI agents so they can read/write only what they need

$ npx skills add eugene1g/agent-safehouse

1.9K stars62 quality82 trustReviewed with permission notesClaude Code1mo since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustGood trust signals with a few areas worth checking before rollout.Review: Documentation summary is thin

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

Claude Code + CLI · 4 targets

shellai-agents

by eugene1gDetailsQuick view

Secure Exec

STRONG · 75TRUST · 75SAFE · EXPERIMENTALCODING

Secure Node.js Execution Without a Sandbox A lightweight library for secure Node.js execution. No containers, no VMs — just npm-compatible sandboxing out of the box.

$ npx skills add rivet-dev/secure-exec

915 stars51 quality75 trustExperimental2mo since pushNeeds review

QualitySolid option that is likely worth shortlisting for production workflows.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

CLI + Codex · 4 targets

javascriptai-agents

by rivet-devDetailsQuick view

SmolVM

STRONG · 73TRUST · 79SAFE · REVIEWEDCODING

Open-source AI sandbox infrastructure with unified API for VMMs -- Firecracker, QEMU and libkrun.

$ npx skills add CelestoAI/SmolVM

614 stars50 quality79 trustReviewed with permission notesBrowser agents2mo since pushNeeds review

QualitySolid option that is likely worth shortlisting for production workflows.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Browser agents + CLI · 4 targets

pythoncomputer-use

by CelestoAIDetailsQuick view

K8e

STRONG · 72TRUST · 76SAFE · REVIEWEDCODING

k8e.sh - OpenSource Agentic AI Sandbox Matrix

$ npx skills add xiaods/k8e

453 stars49 quality76 trustReviewed with permission notes3mo since pushNeeds review

QualitySolid option that is likely worth shortlisting for production workflows.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

CLI + Codex · 4 targets

gokubernetes

by xiaodsDetailsQuick view

Open Design

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · VERIFIEDDESIGN

🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · ima…

$ npx skills add nexu-io/open-design

88.1K stars78 quality91 trustVerifiedClaude Code + OpenAI Agents6d since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…

Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Design and creative · I need my agent to produce design assets, UI directions, presentations, or creative media workflows.

Claude Code + OpenAI Agents · 4 targets

typescriptai-agents

by nexu-ioDetailsQuick view

Lisa

NEEDS REVIEW · 47TRUST · 69SAFE · EXPERIMENTALRESEARCH

Sandbox for automated Linux malware analysis.

$ npx skills add danielpoliakov/lisa

486 stars38 quality69 trustExperimental3y since pushNeeds review

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustPotentially useful, but at least one trust signal needs human inspection.Review: Repository looks stale

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Research agents · I need my agent to research a topic, compare sources, and produce a concise report.

CLI + Codex · 4 targets

pythoniot

by danielpoliakovDetailsQuick view

Deer Flow

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDRESEARCH

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it…

$ npx skills add bytedance/deer-flow

71.1K stars74 quality90 trustReviewedClaude Code2mo since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Research agents · I need my agent to research a topic, compare sources, and produce a concise report.

Claude Code + CLI · 4 targets

pythonmulti-agent

by bytedanceDetailsQuick view

Cua

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDRESEARCH

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows…

$ npx skills add trycua/cua

21.4K stars74 quality91 trustReviewed8d since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Research agents · I need my agent to research a topic, compare sources, and produce a concise report.

CLI + Codex · 4 targets

htmlcomputer-use

by trycuaDetailsQuick view

Pi Less Yolo

PROMISING · 66TRUST · 72SAFE · EXPERIMENTALCODING

Slightly less YOLO version of pi-coding-agent in Docker container sandbox

$ npx skills add cjermain/pi-less-yolo

120 stars45 quality72 trustExperimental2mo since pushNeeds review

QualityUseful candidate, but compare it with alternatives before adopting.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

CLI + Codex · 4 targets

shellcoding-agent

by cjermainDetailsQuick view

Cultivar

PROMISING · 67TRUST · 75SAFE · EXPERIMENTALCODING

Use cultivar to test your Agent Skills, run them in sandboxes, and across different agents.

$ npx skills add pinecone-io/cultivar

37 stars45 quality75 trustExperimentalClaude Code13d since pushNeeds review

QualityUseful candidate, but compare it with alternatives before adopting.Check: Low GitHub adoption signal

TrustGood trust signals with a few areas worth checking before rollout.Review: Low GitHub adoption signal

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

Claude Code + CLI · 4 targets

python

by pinecone-ioDetailsQuick view

Flue

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

The sandbox agent framework.

$ npx skills add withastro/flue

7.5K stars69 quality88 trustReviewed30d since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

CLI + Codex · 4 targets

typescriptllm

by withastroDetailsQuick view

Page 1

Showing the strongest 16 results to keep the registry fast for humans and agents. Refine by use case, platform, stars, or search query for a narrower shortlist.

Try the agent resolve API

AI Agent Skills Directory

Results for “sandbox”

Choose by scenario, quality, and trust signals.

OpenSandbox

Amazing Sandbox

Windows Sandbox

Sandbox Agent

Rancher Desktop

Agent Safehouse

Secure Exec

SmolVM

K8e

Open Design

Lisa

Deer Flow

Cua

Pi Less Yolo

Cultivar

Flue

AI Agent Skills Directory

Results for “sandbox”

Choose by scenario, quality, and trust signals.

OpenSandbox

Amazing Sandbox

Windows Sandbox

Sandbox Agent

Rancher Desktop

Agent Safehouse

Secure Exec

SmolVM

K8e

Open Design

Lisa

Deer Flow

Cua

Pi Less Yolo

Cultivar

Flue

AI Agent Skills Directory

Results for “sandbox”

Choose by scenario, quality, and trust signals.

OpenSandbox

Amazing Sandbox

Windows Sandbox

Sandbox Agent

Rancher Desktop

Agent Safehouse

Secure Exec

SmolVM

K8e

Open Design

Lisa

Deer Flow

Cua

Pi Less Yolo

Cultivar

Flue