Privacy choices: we'd like to measure visits anonymously (our own cookie-free counter plus Google Analytics, which sets its own cookies; no ads) and load Beehiiv's newsletter sign-up, which may set its own cookies. Nothing optional runs until you choose. Privacy policy

AgentScout / Tasks / Agent security and safety / Sandboxes and secure execution

AI sandboxes and secure execution tools

Isolated sandboxes where agents can run code and tools away from your machine and data. Of the 137 tools on our agent security and safety page, 9 fit this narrower job. By pricing: 9 open source. The most-starred open repos here are OpenAI Agents SDK (Python) (30,393 stars), NVIDIA OpenShell (20,733 stars), Agent Governance Toolkit (6,495 stars). Most come from the sandboxes & code execution (3), security & governance (3), MCP servers (2) categories.

Updated

OpenAI Agents SDK (Python) logo

OpenAI Agents SDK (Python)

frameworksOpen source

The OpenAI Agents SDK for Python is an MIT-licensed, lightweight framework for multi-agent workflows. Agents are LLMs with instructions, tools, guardrails and handoffs; sandbox agents work inside a container over long time horizons; realtime and voice agents cover speech pipelines; and built-in tracing shows each run. It is provider-agnostic, working with the OpenAI Responses and Chat Completions APIs and 100+ other LLMs, and has a JavaScript/TypeScript sibling (openai-agents-js).

Added

NVIDIA OpenShell logo

NVIDIA OpenShell

sandboxes & code executionOpen source

OpenShell is NVIDIA's Apache-2.0 safe, private runtime for fleets of autonomous AI agents: each agent runs in an isolated sandbox where declarative YAML policies control which files, networks, packages, APIs and credentials it can touch. The project is moving to the CNCF (ai-openshell); the 0.1.x line, at v0.1.8 on Nov 10, 2026, brought a stable release cadence, new isolation primitives, an expanded extension surface and new APIs.

Added

Agent Governance Toolkit logo

Agent Governance Toolkit

security & governanceOpen source

Microsoft toolkit for policy enforcement, identity and sandboxing for AI agents.

Added

Redamon logo

Redamon

MCP serversOpen source + cloudNot yet checked

Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what.

Added

Mantis logo

Mantis

security & governanceOpen source

Google's toolkit for AI coding agents to autonomously find, reproduce and patch software vulnerabilities in isolated environments.

Added

ToolHive logo

ToolHive

MCP serversOpen sourceNot yet checked

Stacklok platform that runs MCP servers in isolated containers with per-request identity, access policy and observability.

Added

Agent Safehouse logo

Agent Safehouse

sandboxes & code executionOpen source

macOS sandbox for local coding agents that limits file and integration access with deny-first policy profiles.

Added

Perplexity SPACE logo

Perplexity SPACE

sandboxes & code executionOpen source

Perplexity's open-source sandbox platform that runs each agent task in its own Firecracker microVM, with credentials and network access controlled from outside.

Added

Sandlock logo

Sandlock

security & governanceOpen source + cloud

The lightest AI sandbox. A process-based sandbox for Linux, no container, no VM, no privilege, no prompt injection

Added

GitHub repos (9)

RepoGitHub starsLicenceLast push
OpenAI Agents SDK (Python) ↗30,393MIT2026-10-27
NVIDIA OpenShell ↗20,733Apache License 2.02026-10-30
Agent Governance Toolkit ↗6,495MIT2026-10-29
Redamon ↗3,246—2026-10-28
Mantis ↗2,675Apache 2.02026-10-25
ToolHive ↗2,316Apache 2.02026-10-30
Agent Safehouse ↗2,128Apache 2.02026-10-19
Perplexity SPACE ↗2,007Apache 2.02026-10-30
Sandlock ↗591—2026-10-28

9 repos. Stars and licence come from each repo, checked when the listing was last verified.

FAQ

What are the best AI tools for agent security and safety focused on sandboxes and secure execution?

We list 9. The first three by GitHub stars and featured status are OpenAI Agents SDK (Python): The OpenAI Agents SDK for Python is an MIT-licensed, lightweight framework for multi-agent workflows. Agents are LLMs with instructions, tools, guardrails and handoffs; sandbox agents work inside a container over long time horizons; realtime and voice agents cover speech pipelines; and built-in tracing shows each run. It is provider-agnostic, working with the OpenAI Responses and Chat Completions APIs and 100+ other LLMs, and has a JavaScript/TypeScript sibling (openai-agents-js).; NVIDIA OpenShell: OpenShell is NVIDIA's Apache-2.0 safe, private runtime for fleets of autonomous AI agents: each agent runs in an isolated sandbox where declarative YAML policies control which files, networks, packages, APIs and credentials it can touch. The project is moving to the CNCF (ai-openshell); the 0.1.x line, at v0.1.8 on Nov 10, 2026, brought a stable release cadence, new isolation primitives, an expanded extension surface and new APIs.; Agent Governance Toolkit: Microsoft toolkit for policy enforcement, identity and sandboxing for AI agents.

Are there free or open-source options?

Yes: 9 open source. Pricing is as each maker states it.

More from agent security and safety

Tools are grouped by what each says it does. Missing one? Submit it free.