awesome-repositories.com
Blog
awesome-repositories.com

Découvrez les meilleurs dépôts open-source grâce à notre recherche par IA.

ExplorerRecherches sélectionnéesAlternatives open sourceLogiciels auto-hébergésBlogPlan du site
ProjetÀ proposNotre méthodologiePresseServeur MCP
Mentions légalesConfidentialitéConditions d'utilisation
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
microsandbox avatar

microsandbox/microsandbox

0
View on GitHub↗
6,683 stars·329 forks·Rust·Apache-2.0·4 vuesdocs.microsandbox.dev↗

Microsandbox

Microsandbox est un runtime microVM sandbox et un exécuteur de code isolé matériellement conçu pour exécuter du code non fiable. Il fonctionne comme un gestionnaire de machine virtuelle embarqué qui permet aux applications de générer et de contrôler des machines virtuelles légères directement dans le code sans avoir besoin d'un démon en arrière-plan.

Le système fournit un environnement d'exécution sécurisé pour les agents IA en exposant des contrôles serveur qui leur permettent d'exécuter des outils et de gérer des fichiers. Il utilise des formats d'image de conteneur standard et des workflows de volumes pour initialiser les machines virtuelles invitées et implémente un mécanisme de gestion des secrets qui empêche les clés sensibles d'entrer dans la mémoire de la machine virtuelle.

La plateforme couvre le cycle de vie complet de l'orchestration de charges de travail isolées, incluant la création, la surveillance et la suppression des environnements. Elle inclut des capacités de surveillance des ressources CPU et mémoire hors bande, la mise en cache d'images invitées, et l'exécution de commandes immédiates ainsi que de sessions détachées en arrière-plan.

Features

  • Untrusted Code Sandboxes - Provides a runtime that executes untrusted code in disposable hardware-isolated microVMs.
  • Hardware-Level Isolation - Uses microVM technology to provide hardware-backed security boundaries between the host and untrusted workloads.
  • AI Agent Tool Integrations - Provides interfaces that connect AI models to external tools and file management for functional task execution.
  • Agent Interface Servers - Implements a server that exposes local tool definitions and API capabilities to AI clients.
  • Virtual Machine Managers - Functions as an embedded virtual machine manager allowing direct control of VM lifecycles within application code.
  • Embedded VM Managers - Allows spawning and controlling virtual machines directly within code without the need for a background daemon.
  • Workload Orchestration - Manages the lifecycle of multiple microVMs including resource limits, image deployment, and performance monitoring.
  • Isolated Execution Sandboxes - Executes commands and applications within secure, resource-constrained microVM sandboxes.
  • MicroVM Sandboxes - Executes untrusted code inside hardware-isolated microVMs with independent kernels to protect the host system.
  • Agent Execution Environments - Provides an isolated runtime specifically configured for running autonomous agents and their associated tasks.
  • VM Image Bootstrapping - Bootstraps isolated environments using standard container image formats and volume workflows for consistent setup.
  • OCI Virtual Machine Image Management - Supports running standard images from registries using OCI-compatible virtual machine image management.
  • OCI Image Sandboxes - Uses standard container images and volume workflows to initialize isolated guest virtual machines.
  • Sandbox Lifecycle Management - Provides comprehensive controls to create, start, stop, and remove named isolated environments.
  • Sandbox Detachments - Supports executing sandboxes in a background mode to allow for long-lived processes and persistent environments.
  • VM Process Orchestrators - Manages lightweight virtual machines as individual child processes to eliminate the need for a background daemon.
  • Code Executors - Provides isolated environments for running commands with restricted CPU and memory limits to prevent host interference.
  • Code Sandboxing Environments - Runs commands within isolated environments and captures the output for the host application.
  • Runtime Secret Injection - Implements a secure channel for injecting sensitive keys at runtime to prevent them from residing in guest memory.
  • Secret Injection Mechanisms - Implements a secret management mechanism that prevents sensitive keys from entering virtual machine memory.
  • Secrets Management - Handles sensitive keys and credentials to prevent them from ever entering the virtual machine memory.
  • Hypervisor Resource Monitoring - Provides live tracking of CPU, memory, and network statistics for running sandboxes via hypervisor queries.
  • Out-of-Band Management - Tracks CPU and memory usage via the hypervisor using a channel separate from the guest operating system.
  • Sandbox and Virtualization - Self-hosted platform for secure execution of AI code.
  • More to explore - Secure sandbox for code execution.

Historique des stars

Graphique de l'historique des stars pour microsandbox/microsandboxGraphique de l'historique des stars pour microsandbox/microsandbox

Recherche par IA

Explorez plus de dépôts awesome

Décrivez vos besoins en langage naturel — l'IA classe des milliers de projets open source sélectionnés par pertinence.

Start searching with AI

Questions fréquentes

Que fait microsandbox/microsandbox ?

Microsandbox est un runtime microVM sandbox et un exécuteur de code isolé matériellement conçu pour exécuter du code non fiable. Il fonctionne comme un gestionnaire de machine virtuelle embarqué qui permet aux applications de générer et de contrôler des machines virtuelles légères directement dans le code sans avoir besoin d'un démon en arrière-plan.

Quelles sont les fonctionnalités principales de microsandbox/microsandbox ?

Les fonctionnalités principales de microsandbox/microsandbox sont : Untrusted Code Sandboxes, Hardware-Level Isolation, AI Agent Tool Integrations, Agent Interface Servers, Virtual Machine Managers, Embedded VM Managers, Workload Orchestration, Isolated Execution Sandboxes.

Quelles sont les alternatives open-source à microsandbox/microsandbox ?

Les alternatives open-source à microsandbox/microsandbox incluent : superradcompany/microsandbox — Microsandbox is a runtime for creating and managing lightweight, hardware-isolated virtual machines — called sandboxes… zerocore-ai/microsandbox — microsandbox is a platform that runs untrusted code inside hardware-isolated microVMs, each with its own kernel,… kata-containers/runtime — This project is an OCI-compatible container runtime that executes workloads within lightweight virtual machines. By… openai/openai-agents-python — This project is a Python framework for building autonomous, event-driven agent systems. It provides a unified runtime… cirruslabs/tart — Tart is an Apple Silicon virtualization manager used to build and run macOS and Linux virtual machines using native… maiot-io/zenml — ZenML is an extensible machine learning orchestration framework designed to manage the end-to-end lifecycle of data…

Alternatives open source à Microsandbox

Projets open source similaires, classés selon le nombre de fonctionnalités partagées avec Microsandbox.
  • superradcompany/microsandboxAvatar de superradcompany

    superradcompany/microsandbox

    6,570Voir sur GitHub↗

    Microsandbox is a runtime for creating and managing lightweight, hardware-isolated virtual machines — called sandboxes — that boot directly from standard OCI container images. Each sandbox runs as its own host process with a separate kernel, filesystem, and network stack, providing process-per-sandbox isolation. The project includes a command-line tool and multi-language SDKs (Rust, TypeScript, Python, Go) for programmatic lifecycle control, and it communicates with sandbox agents over Unix sockets using a CBOR-encoded protocol. What distinguishes Microsandbox is its combination of host-manag

    Rust
    Voir sur GitHub↗6,570
  • zerocore-ai/microsandboxAvatar de zerocore-ai

    zerocore-ai/microsandbox

    4,802Voir sur GitHub↗

    microsandbox is a platform that runs untrusted code inside hardware-isolated microVMs, each with its own kernel, filesystem, and network stack. It boots directly from standard OCI container images, supports copy-on-write filesystem layers, and integrates with AI agents to execute tool calls and generated code in isolated environments with secret protection. What sets microsandbox apart is its host-side network proxy that enforces firewall rules, intercepts DNS, inspects TLS traffic, and injects secrets at the network boundary without exposing them inside the VM. It provides SSH access to micr

    Rustagentsaiai-generated
    Voir sur GitHub↗4,802
  • kata-containers/runtimeAvatar de kata-containers

    kata-containers/runtime

    2,089Voir sur GitHub↗

    This project is an OCI-compatible container runtime that executes workloads within lightweight virtual machines. By leveraging hardware-based virtualization, it provides strong security isolation between containerized processes and the host operating system, serving as a drop-in replacement for traditional container execution environments. The runtime distinguishes itself through a hypervisor-agnostic architecture that abstracts underlying virtualization operations, allowing for consistent container lifecycle management across different backends. It integrates directly with standard container

    Gocontainercontainerscri-o
    Voir sur GitHub↗2,089
  • openai/openai-agents-pythonAvatar de openai

    openai/openai-agents-python

    27,191Voir sur GitHub↗

    This project is a Python framework for building autonomous, event-driven agent systems. It provides a unified runtime for orchestrating multi-agent workflows, managing persistent conversation state, and executing code within secure, isolated sandbox environments. The framework is designed to handle complex task delegation, allowing agents to invoke other agents as tools while maintaining context across multi-turn interactions. The framework distinguishes itself through its deep integration with the Model Context Protocol, enabling agents to connect to external data sources and remote services

    Pythonagentsaiframework
    Voir sur GitHub↗27,191
Voir les 30 alternatives à Microsandbox→