Execution sandbox

Sandboxie is an operating system-level virtualization tool designed to run Windows applications in isolated, secure environments. By intercepting system calls and redirecting file system and registry modifications to a separate, discardable storage area, it prevents untrusted software from making permanent changes to the host system. This containment ensures that browser history, temporary files, and potential malware remain trapped within the sandbox, protecting the integrity and privacy of the underlying host. The software distinguishes itself through granular control over the isolation env

Dify-sandbox is a secure runtime environment designed for the execution of untrusted code snippets. It functions as a containerized sandbox that isolates processes from the host operating system, ensuring that arbitrary scripts can be run without granting them unauthorized access to sensitive data or critical system resources. The project distinguishes itself through a multi-layered security approach that combines kernel-level isolation with strict resource management. By utilizing Linux namespaces and container-based process isolation, it partitions system resources to maintain visibility bo

This project is an OS-level process sandbox and cross-platform security wrapper for Linux and macOS. It is designed to isolate arbitrary processes from the host machine by restricting filesystem and network access without the use of full containerization. The system functions as a system-call interceptor and access controller, blocking unauthorized operating system calls based on predefined security policies. It employs allowlists and denylists to manage resource requests and monitors for security violations in real time. Capability areas include filesystem access management using glob-patte

This project is a secure container runtime that provides strong isolation for application workloads by implementing a userspace kernel. By intercepting system calls and executing them within a memory-safe, restricted environment, it minimizes the attack surface exposed to the host kernel. It functions as a drop-in engine for standard container orchestration platforms, ensuring compatibility with industry-standard runtime specifications while maintaining a hardened execution boundary. The runtime distinguishes itself through its ability to virtualize core system resources, including an indepen

Kata Containers is an OCI container runtime that launches containers inside lightweight virtual machines to combine hardware-level isolation with container operational speed. It functions as a hardware-isolated container engine and lightweight VM hypervisor, providing a virtual machine monitor interface that abstracts multiple hypervisors to optimize for performance or specific hardware emulation. The project distinguishes itself through a confidential computing runtime that leverages hardware-backed trusted execution environments, such as Intel TDX and AMD SEV-SNP, to protect data in use. It

This project provides secure, containerized infrastructure designed for autonomous agents, remote code execution, and cloud development. It functions as a sandboxed environment where AI agents and external processes can execute code, run shell commands, and manage files while remaining isolated from the host system. The system distinguishes itself by implementing the Model Context Protocol, allowing it to act as a standardized tool server that exposes browser and filesystem capabilities to compatible clients. It further integrates headless browser automation, enabling programmatic web navigat

OpenShell is a security framework and sandboxed execution runtime for autonomous AI agents. It provides isolated environments using containers and virtual machines to protect host infrastructure and sensitive data from unauthorized access during agent execution. The system distinguishes itself by combining hardware-accelerated passthrough for host GPU access with a security gateway that intercepts model API calls. This gateway manages credentials by stripping caller information and injecting backend secrets, ensuring sensitive API keys remain off the local filesystem. The platform covers bro

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

container-use is a containerized AI execution environment and code sandbox designed to provide a secure space for AI coding agents to execute commands and build applications. It functions as a workspace orchestrator that provisions isolated containers mapped to git branches, allowing multiple agents to operate in parallel without state conflicts or affecting the host system. The project serves as a Model Context Protocol server, bridging AI agents to containerized environments for standardized tool access. It enables a workflow for reviewing and merging changes made by agents within these iso

Deno is a high-performance runtime for JavaScript and TypeScript that prioritizes security and developer productivity. Built on the V8 engine, it provides a secure execution environment that enforces a default-deny security model, requiring explicit user authorization for access to system resources like the file system, network, and environment variables. The runtime natively supports modern web-standard APIs, ensuring consistent behavior and portability across different environments. What distinguishes Deno is its integrated approach to the software development lifecycle. It bundles essentia

E2B is a cloud-based infrastructure platform designed to provide secure, isolated execution environments for code and shell commands. It functions as an ephemeral orchestrator that provisions lightweight virtual machines, allowing developers and autonomous agents to run untrusted processes within a sandbox that is completely separated from the host system. The platform distinguishes itself through its focus on programmable, serverless workspaces that support the full lifecycle of cloud-based development. By utilizing hardware-level isolation and snapshot-based resumption, it enables the near-

Linux process isolation tool using namespaces, resource limits, and seccomp-bpf syscall filters.

Bubblewrap is a Linux sandbox runner that creates lightweight, isolated execution environments for running untrusted applications. It combines Linux user, mount, network, PID, and UTS namespaces with seccomp-BPF system call filtering to restrict filesystem, network, process, and inter-process communication access. The project provides comprehensive process isolation by giving each sandbox its own private tmpfs root with selective bind-mounts, a separate network stack containing only a loopback interface, an independent process ID space, and remapped user and group identifiers. It applies secc

Firejail is a Linux application sandbox and kernel security wrapper that isolates untrusted applications from the host system. It uses kernel namespaces and seccomp filters to restrict filesystem access, drop kernel capabilities, and limit the system attack surface. The project is distinguished by its use of predefined security profiles to automatically apply filesystem restrictions and syscall limits based on the executable being launched. It provides specialized isolation for portable packages such as AppImages and implements X11 display isolation via proxy servers to prevent keyboard loggi

This project provides a secure, containerized execution engine designed to run untrusted code within isolated environments. It functions as a library for integrating code interpretation into autonomous agents and intelligent assistant workflows, ensuring that host systems remain protected while enabling dynamic data processing and file manipulation. The platform distinguishes itself through a multi-backend architecture that abstracts diverse container runtimes, allowing for flexible deployment and automated backend failover. It supports interactive, multi-turn workflows by maintaining persist

The sandbox-sdk is a development kit designed for building secure, isolated execution environments on a global edge network. It provides a framework for creating ephemeral, containerized workspaces that allow developers to run untrusted code, manage build tasks, and host automated scripts without compromising host system security. By leveraging a serverless runtime, the platform enables the deployment of these environments directly at the network edge to ensure low-latency performance. The platform distinguishes itself by integrating language models with sandboxed execution, facilitating the

Firecracker is a virtual machine monitor that leverages hardware-assisted virtualization to create and manage isolated execution environments. It functions as a lightweight runtime designed to launch virtual machines with minimal memory overhead and near-instantaneous startup times, providing the security of traditional hardware virtualization with the efficiency of containerized workloads. The project distinguishes itself through a security-focused architecture that enforces strict process boundaries using system-level barriers and restricted user privileges. It minimizes the attack surface

Sysbox is an OCI-compliant container runtime that provides virtual-machine-level isolation for containers without requiring hardware virtualization. It achieves this by mapping the container's root user to an unprivileged host user ID range, virtualizing the /proc and /sys filesystems, and applying seccomp-BPF system call filtering, all while using cgroup v2 for resource partitioning. The runtime enables running system-level software such as systemd, Docker, and Kubernetes inside unprivileged containers without requiring special images or privileged mode. It supports nested namespace stacking

Isolate is a low-level sandbox designed to execute untrusted programs within a strictly controlled environment. It functions as a process isolation engine that prevents potentially harmful code from interacting with or damaging the host operating system. The tool leverages Linux kernel primitives, including namespaces and control groups, to partition system resources and enforce hardware usage boundaries. By applying filesystem virtualization and system call filtering, it restricts the visibility and interaction of a process with the host, ensuring that untrusted applications operate only wit

Bubblewrap is an unprivileged sandbox execution utility for Linux that isolates processes from the host system. It creates secure environments by leveraging Linux namespaces to separate system resources, including network, PID, and IPC stacks. The project distinguishes itself by enabling the execution of untrusted software without requiring root privileges on the host machine. It prevents privilege escalation by disabling the execution of setuid binaries and uses user identity mapping to isolate process permissions from the host operating system. The tool manages a comprehensive security sur

Isolated-vm is a library for creating secure, memory-isolated JavaScript execution environments within Node.js. It functions as a manager for the underlying engine, allowing developers to instantiate multiple independent execution contexts that share no memory or global state. This architecture is designed to support the execution of untrusted third-party code while preventing interference with the main application process. The project distinguishes itself by enforcing strict resource constraints, including memory limits and CPU execution timeouts, to ensure host system stability. It provides

An MCP server to create secure code sandbox environment for executing code within Docker containers. This MCP server provides AI applications with a safe and isolated environment for running code while maintaining security through containerization.

rlm is an LLM code execution engine and orchestration framework designed to coordinate multiple language model calls and recursive sub-tasks through a programmable environment. It provides a sandboxed REPL environment and a recursive context processor to handle inputs that exceed standard token limits by programmatically decomposing prompts. The project differentiates itself through a reinforcement learning training harness used to teach models how to utilize recursive calls and code execution. It includes a reasoning visualization system that records and renders execution trajectories to ana