Open-source alternatives to CubeSandbox

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

Moltworker is an AI agent sandbox and model orchestrator designed for the secure execution of untrusted code and shell commands generated by large language models. It functions as a gateway proxy that routes requests to multiple AI providers through a unified interface, integrating a container runtime backed by S3-compatible object storage to persist state across ephemeral lifecycles. The system distinguishes itself by combining an AI model orchestrator with a headless browser controller for automated web scraping and screenshot capture. It manages the full lifecycle of AI agents, including m

OpenSquilla is an LLM agent orchestration framework designed to coordinate multi-step AI workflows and tool execution using directed acyclic graphs. It functions as a centralized system for managing specialized skill packages and executing complex reasoning sequences. The project distinguishes itself through a routing gateway that directs tasks to different AI providers based on complexity, cost, and performance. It utilizes a multi-tier AI memory system that organizes working, episodic, and semantic knowledge using local embeddings and SQLite, alongside a secure execution sandbox that isolat

OpenSandbox is a secure execution environment and runtime designed for running untrusted code and scripts generated by AI agents. It utilizes a containerized code execution engine and microVM-based isolation to protect host systems from malicious actions while providing isolated virtual environments. The project features a sandbox server based on the Model Context Protocol to automate the creation and control of virtual workspaces. It supports the deployment of secure remote desktop hosts, including headless web browsers and editor instances, for automated interaction. The system includes an

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

Fragments is an open-source AI code generation sandbox that produces code automatically based on user prompts and executes it inside isolated cloud environments. The project provides a secure foundation for running AI-generated code by sandboxing execution away from the host system, preventing potential harm while allowing users to see results immediately. The sandbox supports customization through configurable execution environments defined via Dockerfiles, enabling code to run in specific runtimes or frameworks. Users can integrate different language models and model providers by registerin

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

Monty is a sandboxed execution environment designed primarily for running Python code generated by AI models. It provides a secure, isolated runtime that blocks host access, enforces resource limits, and supports pre-execution type checking against built-in type hints to catch signature mismatches before code runs. The sandbox can persist its interpreter state at external function calls, allowing execution sessions to be serialized, stored, and later resumed from a file or database. What distinguishes Monty is its combination of stateful, resumable execution with multi-language native embeddi

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

Hyperlight is an embedded virtual machine manager designed to execute guest binaries within hardware-isolated code sandboxes. It utilizes a KVM micro-VM manager to run untrusted third-party code, enforcing strict memory boundaries to prevent unauthorized host access. The project features a guest-host function bridge that facilitates bidirectional communication and a state snapshot tool for saving and restoring the memory state of a sandbox to reduce startup latency. The system includes a toolchain for guest binary cross-compilation and mechanisms for managing resource constraints, such as fi

Open-SWE is an asynchronous software engineering agent and orchestrator designed to automate end-to-end coding tasks and pull request reviews. It functions as a middleware framework that coordinates long-running AI operations across multiple subagents, utilizing state persistence and human-in-the-loop oversight to manage complex workflows. The system is distinguished by its use of isolated remote Linux sandboxes for secure code execution and shell command processing. It features a webhook-driven integration platform that triggers automated engineering tasks via mentions and events in GitHub,

Sandbox Agent is a platform designed to manage, secure, and orchestrate autonomous coding assistants. It provides a standardized infrastructure for executing untrusted code and managing agent lifecycles within isolated, containerized environments. By decoupling agent execution from client connections, the platform ensures that session states remain persistent across process restarts and network interruptions. The project distinguishes itself through a capability-based security model that enforces granular permission checks on tool usage, ensuring that autonomous processes operate within defin

CodeWhale is an AI coding agent orchestrator and development harness designed to coordinate autonomous agents that read, edit, and verify code. It provides a secure environment for AI agents to perform multi-step software engineering tasks, utilizing a sandboxed execution model to isolate shell commands and protect the host system. The system distinguishes itself by spawning multiple independent agents in parallel to handle separate investigation or implementation slices simultaneously. It employs a multi-model gateway to route requests across various cloud APIs and local servers, and utilize

Lucet is a WebAssembly runtime and sandboxing compiler that translates WebAssembly bytecode into native machine code. It serves as a secure execution environment and native code generator designed to run untrusted code while preventing unauthorized access to host system resources. The project focuses on high-performance sandboxing by using ahead-of-time compilation to achieve near-native execution speeds. It implements software-based fault isolation and a host-call interface to manage secure communication and data exchange between the isolated module and the external host application. The sy

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

RD-Agent is an autonomous framework designed to orchestrate multi-step software engineering and data science workflows. By leveraging large language models, the system decomposes complex technical requirements into actionable research, planning, and execution phases, ultimately generating and running code to solve specific development tasks. The platform distinguishes itself through a containerized execution sandbox that ensures secure dependency management and system stability for all autonomously generated code. It employs multi-agent orchestration to manage iterative feedback loops, allowi

This project is a cloud-based web IDE and development workspace that provides a professional code editor and execution environments directly within the browser. It functions as a browser-based code execution engine for rapid prototyping and a scalable cloud workspace for managing repositories and writing code without local environment configuration. The system features secure sandboxing for isolated development, allowing untrusted or experimental code to run in separated virtual environments. It supports both client-side execution via browser-based bundling and server-side execution through a

This repository is a technical documentation site and a collection of guides and references for implementing networking, security, and cloud infrastructure services. It functions as a static-site generated portal and a headless content platform, separating source files from the presentation layer to enable flexible rendering. The project utilizes markdown-based documentation stored in a version-controlled Git repository. It provides specialized technical content including an AI platform documentation for building agents and managing inference, a cloud infrastructure guide for DNS and CDN conf

DB-GPT is an agentic data analysis platform and business intelligence AI that functions as a large language model data assistant. It provides a text-to-SQL interface and a sandboxed code execution environment to translate natural language into executable database queries and Python scripts. The platform utilizes iterative agentic reasoning to plan and execute multi-step data analysis workflows through tool calls. It features a modular skill-based extension system that allows domain knowledge and analysis workflows to be packaged into reusable functional components. The system integrates data

AstrBot is an orchestration framework designed for building and managing autonomous agents that integrate multimodal artificial intelligence with secure, isolated execution environments. It serves as a platform for coordinating complex agentic workflows, allowing users to connect diverse language, speech, and vision models while maintaining personalized agent personas and domain-specific knowledge bases. The platform distinguishes itself through a modular plugin architecture and a centralized visual dashboard, which together enable users to extend agent capabilities and manage operational set

Agent Zero is an autonomous AI agent framework designed to execute complex, multi-step workflows by managing its own environment, persistent memory, and external tool interactions. It functions as a Python-based automation library that enables agents to write code, execute terminal commands, and perform system-level tasks independently. The system is built to handle large-scale operations through hierarchical agent delegation, allowing for the coordination of subordinate agents to maintain focus and context. The platform distinguishes itself through a focus on secure, isolated execution and s

LXD is a unified platform for managing both system containers and virtual machines through a single REST API and command-line interface. It provides a programmatic HTTP interface for controlling the full lifecycle of instances, enabling automation and integration with external tools. The system runs unprivileged containers with per-instance UID/GID mappings, seccomp filters, and AppArmor profiles for kernel-level isolation, while supporting multiple storage backends including directory, Btrfs, LVM, ZFS, Ceph, LINSTOR, and TrueNAS through a unified driver interface. The platform distinguishes

PySyft is a privacy-preserving machine learning framework and remote computation engine. It functions as a decentralized data analysis orchestrator that allows for the execution of data science workflows on remote servers without requiring the transfer of raw private data from the host device. The platform provides a secure collaboration environment where data owners manage permissions and authorize specific collaborators to run computations. It differentiates its workflow by utilizing mock data for local development and validation before submitting final analysis jobs to private remote serve

Lua is an embeddable scripting language written in ISO C, designed to be integrated into host applications for runtime customization. It provides a C-based scripting engine and a prototype-based object model that utilizes associative arrays and metatables to implement inheritance and complex data structures. The language features a cooperative multitasking system that manages concurrent execution threads via coroutines and an incremental garbage collector for automatic memory management. It includes a safe code sandbox to isolate global state and run untrusted scripts within a protected envir

This project is a command line interface and GitHub CLI extension that functions as an AI coding agent and model orchestrator. It enables the writing of code and the management of repositories through natural language prompts using large language models. The tool implements the Agent Client Protocol to act as a standardized agent server for external editors. It features a provider-agnostic routing system that allows switching between different hosted AI models or external compatible endpoints. Capabilities include the automation of Git workflows, such as managing pull requests and issues, an

The Gemini Cookbook is a comprehensive collection of implementation patterns, code samples, and development guides designed for building applications with Google Gemini models. It serves as a central resource for developers to integrate multimodal generative artificial intelligence into their software, providing the necessary frameworks to manage model interactions, stateful workflows, and structured data extraction. The repository distinguishes itself by offering specialized toolkits for autonomous agent orchestration, enabling the construction of agents that can execute code, browse the web

Ironclaw is an LLM orchestration framework and AI agent gateway designed to connect large language models with external tools, messaging interfaces, and persistent memory systems. It functions as a communication layer that routes interactions between users and AI models via HTTP webhooks and various messaging channels. The system focuses on secure tool execution through a WebAssembly sandbox and isolated containers, which allows the framework to run untrusted code and dynamically generate new tools from natural language descriptions. Security middleware provides prompt injection defense and s