Open-source alternatives to Llm Sandbox

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

Acontext is an LLM orchestration backend and agent memory framework designed to manage session state and knowledge for AI agents. It functions as a context manager and orchestration layer that integrates model providers with a secure code sandbox and a zero-knowledge data store. The project is distinguished by its approach to knowledge distillation, capturing agent learnings as reusable Markdown skills and structured memory files. It provides a secure execution environment where shell commands and scripts run in isolated containers with the ability to mount these persistent skill files direct

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

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

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

Daytona is a cloud-native development environment platform designed to orchestrate ephemeral, containerized workspaces. It provides a centralized system for managing reproducible coding environments as code, ensuring consistency across distributed teams by abstracting the underlying infrastructure. By utilizing declarative configuration, the platform automates the entire lifecycle of development sandboxes, from initial provisioning to resource governance. The platform distinguishes itself through its infrastructure-agnostic runner layer, which allows development environments to be deployed ac

This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified architecture for orchestrating multi-agent societies, where specialized agents collaborate through roleplay to decompose and solve complex tasks. The system integrates language models with external environments, enabling agents to perform real-world actions through a standardized tool-calling abstraction layer. The framework distinguishes itself through its focus on iterative reasoning and data reliability. It employs automated feedback loops to refine agent outputs and self-eva

ZenML is an orchestration platform designed for building, deploying, and monitoring reproducible machine learning pipelines and agentic workflows. It provides a unified framework that manages the entire lifecycle of machine learning assets, from data processing and model training to the deployment of persistent inference services. By decoupling pipeline logic from underlying compute and storage, the platform enables teams to transition workflows seamlessly from local development environments to production-grade cloud infrastructure. The platform distinguishes itself through a service-oriented

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

OpenSandbox is a secure sandbox runtime and containerized code execution engine designed to run AI-generated code and scripts in isolated environments. It serves as a workload orchestrator that prevents host system contamination by utilizing kernel-level isolation to execute arbitrary commands and scripts. The project distinguishes itself by providing a model context server that bridges large language models to the sandbox for performing file operations and system commands. It also includes a remote GUI sandbox that supports browser automation and desktop interfaces via remote access protocol

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

Open Interpreter is an autonomous agent runtime that translates natural language instructions into executable code to interact with local software and operating systems. It functions as an orchestration framework that connects language models to a secure execution environment, enabling the development of agents capable of managing system resources and performing complex tasks. To ensure safety, the system mandates explicit user verification before executing any generated code and provides robust isolation through containerized sandboxing. The project distinguishes itself through its deep inte

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-

Open Interpreter is a coding agent that uses large language models to write and execute code directly on a local host machine. It functions as a system for performing operating system tasks and file manipulations through a natural language interface. The project features a model orchestrator that allows switching between different language model providers and emulation harnesses. It employs a loop-based reasoning process to iteratively generate code and process execution output until a goal is achieved. Its capabilities include cross-platform system automation, local model integration for da

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

Javascript Playgrounds is a browser-based code execution engine designed for running untrusted JavaScript snippets and managing interactive playgrounds. The system isolates user-submitted code inside dedicated web workers to prevent main thread blocking and protect the host environment, while supporting dynamic module loading that fetches external libraries and third-party scripts on demand. The platform includes architectural tools for mobile device simulation, rendering application output inside configurable viewport wrappers with adjustable platform dimensions and status bar styling. Debug

This project is an interactive programming curriculum and educational system designed to teach computer science and software engineering. It provides a structured set of courses and professional roadmaps focused on backend engineering, DevOps, and systems fundamentals. The platform is distinguished by an AI-powered coding tutor that provides Socratic guidance and contextual hints to help students find solutions independently. It features a browser-based code sandbox using WebAssembly to eliminate local environment setup, alongside automated test-based grading and spaced-repetition logic to re

CubeSandbox is a Kubernetes-based platform for executing AI agents in secure, lightweight environments. It provides a code execution sandbox that uses hardware isolation and dedicated guest kernels to run untrusted code without risking the host system. The project features a network egress firewall that restricts outbound communication via domain allowlists and audit logging. It also includes a container snapshotting manager capable of capturing the runtime memory and disk state of environments to enable instant cloning and recovery. The platform covers cluster orchestration through a web-ba

Youtu Agent is an open-source framework for building, running, and evaluating autonomous agents powered by large language models. It provides the core infrastructure for creating agents that follow reasoning loops, use toolkits, and coordinate with other agents to solve complex tasks, all managed through YAML-driven configuration files. The framework distinguishes itself through its support for multi-agent orchestration, where a planner agent decomposes tasks and coordinates specialized worker agents, and through its integration with the Model Context Protocol for connecting to external toolk

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

Judge0 is an online code execution engine and multi-language compiler API designed to compile and run source code within isolated sandboxes. It functions as an asynchronous job processor that handles code submissions via a queue and provides a secure environment to run arbitrary programs while preventing unauthorized system access. The system distinguishes itself through a multi-stage compilation pipeline and a flexible execution model that supports both single-file submissions and multi-file program execution via archives. It employs an isolate-based sandboxing mechanism to enforce strict ha

This project provides a programmatic interface and framework for integrating large language models with secure, stateful, and multimodal code execution environments. It functions as a code interpreter API that enables the execution of arbitrary Python scripts within isolated sandboxed runtimes. The system supports multimodal data analysis by processing combined text and file inputs to generate visualizations and computational results. It manages stateful workflows by maintaining conversation memory and session history, allowing language models to complete multi-step technical tasks. The fram

Nanoclaw is an LLM agent orchestrator and multi-platform chat gateway designed to deploy and manage isolated AI agents. It provides a containerized runtime that executes agents within sandboxed Linux containers, ensuring filesystem and state isolation through dedicated workspaces and host bind-mounts. The project distinguishes itself through a unified routing pipeline that connects agents to diverse messaging platforms, including WhatsApp, Discord, Slack, Telegram, Signal, and iMessage. It integrates the Model Context Protocol to extend agent capabilities via managed external data and functio

This project is a framework for the autonomous discovery and remediation of security vulnerabilities using large language model agents. It functions as a security research pipeline that automates the process of reconnaissance, crash discovery, and exploitability analysis to identify reproducible software bugs. The system distinguishes itself by utilizing a containerized agent sandbox that restricts network egress and filesystem access to prevent host compromise. It employs a specialized patch generation and validation loop, which includes adversarial re-attack testing where a fresh agent atte

Activepieces is an open-source, self-hosted workflow automation platform designed to connect third-party applications through modular triggers and actions. It provides a low-code integration framework that allows users to build, manage, and execute complex business logic sequences within isolated, sandboxed environments. The platform distinguishes itself through its focus on embeddability and enterprise-grade security. It features an embedded automation builder that can be integrated into external applications via iframes, supported by comprehensive identity and access management tools such a

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

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