HomeProjectsArticlesPK BoardAbout
Explore Projects

Microsandbox

Active
GitHub Rust Apache-2.0

Description

Secure, local, cross-platform and programmable sandboxes for AI agents. Provides strict resource isolation using microVM technology.

Key Features

  • Hardware-level isolation with microVM technology
  • Instant startup with average boot times under 100ms
  • Embeddable SDKs for Rust, Python, TypeScript, and Go
  • Secrets that cannot leak - keys never enter the VM
  • OCI compatible - runs standard Docker container images
  • Long-running sandboxes with detached mode support

Use Cases

💡 Secure code execution sandbox for AI agents
💡 Isolated testing environments for CI/CD pipelines
💡 Multi-tenant SaaS application isolation
💡 Educational platforms requiring safe code execution
💡 Long-running background task processing with security

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (8.1k stars)
  • • Permissive open-source license (Apache-2.0)

Tags

rust agent tools security devops

Categories

📊 Observability 🛡️ Security & Guardrails 🏗️ Sandbox & Execution

Quick Start

Install via cargo add microsandbox (Rust), uv add microsandbox (Python), npm i microsandbox (TypeScript), or go get (Go). For CLI, run npx microsandbox run debian or install globally with curl -fsSL https://install.microsandbox.dev | sh. Requires Linux with KVM or macOS with Apple Silicon.
Visit GitHub Visit Website View Docs

Related Projects

OpenShell

8.5k · Rust
Active A

OpenShell is the safe, private runtime for autonomous AI agents, developed by NVIDIA. Provides controlled execution environments and resource management.

rustagentframework +2
  • · Sandboxed execution environments protecting data, credentials, and infrastructure with declarative YAML policies
  • · Four defense-in-depth layers: filesystem, network, process, and inference policy enforcement
  • · Hot-reloadable network and inference policies via `openshell policy set` without restarting sandboxes
View full details → View on GitHub

Agent Governance Toolkit

6.2k · Python
Active A

Microsoft's AI Agent Governance Toolkit providing policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

securityevaluationpython +2
  • · Deterministic policy enforcement engine: intercepts and evaluates all operations before model output reaches tool calls, with YAML policy files defining allow/deny/approval-required rules — denied actions are structurally impossible
  • · Zero-trust identity and audit trail: assigns unique DIDs to each agent, generates tamper-evident audit records for every operation including active policy, request content, and decision rationale
  • · Multi-language SDK support: Python, TypeScript, .NET, Rust, and Go SDKs with unified policy evaluation APIs covering major development stacks
View full details → View on GitHub