boxlite

Local-first sandbox for AI agents.

Stars: 1038

Visit

BoxLite is an embedded, lightweight micro-VM runtime designed for AI agents running OCI containers with hardware-level isolation. It is built for high concurrency with no daemon required, offering features like lightweight VMs, high concurrency, hardware isolation, embeddability, and OCI compatibility. Users can spin up 'Boxes' to run containers for AI agent sandboxes and multi-tenant code execution scenarios where Docker alone is insufficient and full VM infrastructure is too heavy. BoxLite supports Python, Node.js, and Rust with quick start guides for each, along with features like CPU/memory limits, storage options, networking capabilities, security layers, and image registry configuration. The tool provides SDKs for Python and Node.js, with Go support coming soon. It offers detailed documentation, examples, and architecture insights for users to understand how BoxLite works under the hood.

README:

BoxLite

Embedded, lightweight micro-VM runtime for AI agents running OCI containers with hardware-level isolation — built for high concurrency, no daemon required.

What is BoxLite?

BoxLite lets you spin up lightweight VMs ("Boxes") and run OCI containers inside them. It's designed for use cases like AI agent sandboxes and multi-tenant code execution, where Docker alone isn't enough and full VM infrastructure is too heavy.

Why BoxLite

Lightweight: small footprint, fast-starting Boxes, minimal operational overhead.
High concurrency: async-first API designed to run many Boxes in parallel; stream stdout/stderr.
Hardware isolation: each Box has its own kernel (not just namespaces).
Embeddable: link a library; no root; no background service to manage.
OCI compatible: use Docker/OCI images (python:slim, node:alpine, alpine:latest).

Python Quick Start

View guide

Install

pip install boxlite

Requires Python 3.10+.

Run

import asyncio
import boxlite


async def main():
    async with boxlite.SimpleBox(image="python:slim") as box:
        result = await box.exec("python", "-c", "print('Hello from BoxLite!')")
        print(result.stdout)


asyncio.run(main())

Node.js Quick Start

View guide

Install

npm install @boxlite-ai/boxlite

Requires Node.js 18+.

Run

import { SimpleBox } from '@boxlite-ai/boxlite';

async function main() {
  const box = new SimpleBox({ image: 'python:slim' });
  try {
    const result = await box.exec('python', '-c', "print('Hello from BoxLite!')");
    console.log(result.stdout);
  } finally {
    await box.stop();
  }
}

main();

Rust Quick Start

View guide

Install

[dependencies]
boxlite = { git = "https://github.com/boxlite-ai/boxlite" }

Run

use boxlite::{BoxCommand, BoxOptions, BoxliteRuntime, RootfsSpec};
use futures::StreamExt;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let runtime = BoxliteRuntime::default_runtime();
    let options = BoxOptions {
        rootfs: RootfsSpec::Image("alpine:latest".into()),
        ..Default::default()
    };

    let litebox = runtime.create(options, None).await?;
    let mut execution = litebox
        .exec(BoxCommand::new("echo").arg("Hello from BoxLite!"))
        .await?;

    let mut stdout = execution.stdout().unwrap();
    while let Some(line) = stdout.next().await {
        println!("{}", line);
    }

    Ok(())
}

Next steps

Run more real-world scenarios in Examples
Learn how images, disks, networking, and isolation work in Architecture

Features

Compute: CPU/memory limits, async-first API, streaming stdout/stderr, metrics
Storage: volume mounts (ro/rw), persistent disks (QCOW2), copy-on-write
Networking: outbound internet, port forwarding (TCP/UDP), network metrics
Images: OCI pull + caching, custom rootfs support
Security: hardware isolation (KVM/HVF), OS sandboxing (seccomp/sandbox-exec), resource limits
Image Registry Configuration: Configure custom registries via config file (--config), CLI flags (--registry), or SDK options. See the configuration guide.
SDKs: Python (stable), Node.js (v0.1.6); Go coming soon

Architecture

High-level overview of how BoxLite embeds a runtime and runs OCI containers inside micro-VMs. For details, see Architecture.

Show diagram

┌──────────────────────────────────────────────────────────────┐
│  Your Application                                            │
│  ┌───────────────────────────────────────────────────────┐   │
│  │  BoxLite Runtime (embedded library)                   │   │
│  │                                                        │   │
│  │  ╔════════════════════════════════════════════════╗   │   │
│  │  ║ Jailer (OS-level sandbox)                      ║   │   │
│  │  ║  ┌──────────┐  ┌──────────┐  ┌──────────┐      ║   │   │
│  │  ║  │  Box A   │  │  Box B   │  │  Box C   │      ║   │   │
│  │  ║  │ (VM+Shim)│  │ (VM+Shim)│  │ (VM+Shim)│      ║   │   │
│  │  ║  │┌────────┐│  │┌────────┐│  │┌────────┐│      ║   │   │
│  │  ║  ││Container││  ││Container││  ││Container││      ║   │   │
│  │  ║  │└────────┘│  │└────────┘│  │└────────┘│      ║   │   │
│  │  ║  └──────────┘  └──────────┘  └──────────┘      ║   │   │
│  │  ╚════════════════════════════════════════════════╝   │   │
│  └───────────────────────────────────────────────────────┘   │
└──────────────────────────────────────────────────────────────┘
                              │
              Hardware Virtualization + OS Sandboxing
             (KVM/Hypervisor.framework + seccomp/sandbox-exec)

Security Layers:

Hardware isolation (KVM/Hypervisor.framework)
OS-level sandboxing (seccomp on Linux, sandbox-exec on macOS)
Resource limits (cgroups, rlimits)
Environment sanitization

Documentation

API Reference — Coming soon
Examples — Sample code for common use cases
Architecture — How BoxLite works under the hood

Supported Platforms

Platform	Architecture	Status
macOS	Apple Silicon (ARM64)	✅ Supported
Linux	x86_64	✅ Supported
Linux	ARM64	✅ Supported
Windows (WSL2)	x86_64	✅ Supported
macOS	Intel (x86_64)	❌ Not supported

System Requirements

Platform	Requirements
macOS	Apple Silicon, macOS 12+
Linux	KVM enabled (`/dev/kvm` accessible)
Windows (WSL2)	WSL2 with KVM support, user in `kvm` group
Python	3.10+

Getting Help

GitHub Issues — Bug reports and feature requests
Discord — Questions and community support

Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

License

Licensed under the Apache License, Version 2.0. See LICENSE for details.

For Tasks:

Click tags to check more tools for each tasks

run containers manage ai agents sandbox code execution spin up lightweight vms stream stdout/stderr

For Jobs:

devops engineer ai engineer cloud architect software developer system administrator

Alternative AI tools for boxlite

Similar Open Source Tools

boxlite

github

: 1.0k

AgentX

AgentX is a next-generation open-source AI agent development framework and runtime platform. It provides an event-driven runtime with a simple framework and minimal UI. The platform is ready-to-use and offers features like multi-user support, session persistence, real-time streaming, and Docker readiness. Users can build AI Agent applications with event-driven architecture using TypeScript for server-side (Node.js) and client-side (Browser/React) development. AgentX also includes comprehensive documentation, core concepts, guides, API references, and various packages for different functionalities. The architecture follows an event-driven design with layered components for server-side and client-side interactions.

github

: 75

vibium

Vibium is a browser automation infrastructure designed for AI agents, providing a single binary that manages browser lifecycle, WebDriver BiDi protocol, and an MCP server. It offers zero configuration, AI-native capabilities, and is lightweight with no runtime dependencies. It is suitable for AI agents, test automation, and any tasks requiring browser interaction.

github

: 2.6k

openakita

OpenAkita is a self-evolving AI Agent framework that autonomously learns new skills, performs daily self-checks and repairs, accumulates experience from task execution, and persists until the task is done. It auto-generates skills, installs dependencies, learns from mistakes, and remembers preferences. The framework is standards-based, multi-platform, and provides a Setup Center GUI for intuitive installation and configuration. It features self-learning and evolution mechanisms, a Ralph Wiggum Mode for persistent execution, multi-LLM endpoints, multi-platform IM support, desktop automation, multi-agent architecture, scheduled tasks, identity and memory management, a tool system, and a guided wizard for setup.

github

: 54

myclaw

myclaw is a personal AI assistant built on agentsdk-go that offers a CLI agent for single message or interactive REPL mode, full orchestration with channels, cron, and heartbeat, support for various messaging channels like Telegram, Feishu, WeCom, WhatsApp, and a web UI, multi-provider support for Anthropic and OpenAI models, image recognition and document processing, scheduled tasks with JSON persistence, long-term and daily memory storage, custom skill loading, and more. It provides a comprehensive solution for interacting with AI models and managing tasks efficiently.

github

: 127

Shannon

Shannon is a battle-tested infrastructure for AI agents that solves problems at scale, such as runaway costs, non-deterministic failures, and security concerns. It offers features like intelligent caching, deterministic replay of workflows, time-travel debugging, WASI sandboxing, and hot-swapping between LLM providers. Shannon allows users to ship faster with zero configuration multi-agent setup, multiple AI patterns, time-travel debugging, and hot configuration changes. It is production-ready with features like WASI sandbox, token budget control, policy engine (OPA), and multi-tenancy. Shannon helps scale without breaking by reducing costs, being provider agnostic, observable by default, and designed for horizontal scaling with Temporal workflow orchestration.

github

: 258

mesh

MCP Mesh is an open-source control plane for MCP traffic that provides a unified layer for authentication, routing, and observability. It replaces multiple integrations with a single production endpoint, simplifying configuration management. Built for multi-tenant organizations, it offers workspace/project scoping for policies, credentials, and logs. With core capabilities like MeshContext, AccessControl, and OpenTelemetry, it ensures fine-grained RBAC, full tracing, and metrics for tools and workflows. Users can define tools with input/output validation, access control checks, audit logging, and OpenTelemetry traces. The project structure includes apps for full-stack MCP Mesh, encryption, observability, and more, with deployment options ranging from Docker to Kubernetes. The tech stack includes Bun/Node runtime, TypeScript, Hono API, React, Kysely ORM, and Better Auth for OAuth and API keys.

github

: 329

solo-server

Solo Server is a lightweight server designed for managing hardware-aware inference. It provides seamless setup through a simple CLI and HTTP servers, an open model registry for pulling models from platforms like Ollama and Hugging Face, cross-platform compatibility for effortless deployment of AI models on hardware, and a configurable framework that auto-detects hardware components (CPU, GPU, RAM) and sets optimal configurations.

github

: 225

helix

HelixML is a private GenAI platform that allows users to deploy the best of open AI in their own data center or VPC while retaining complete data security and control. It includes support for fine-tuning models with drag-and-drop functionality. HelixML brings the best of open source AI to businesses in an ergonomic and scalable way, optimizing the tradeoff between GPU memory and latency.

github

: 715

kweaver

KWeaver is an open-source ecosystem for building, deploying, and running decision intelligence AI applications. It adopts ontology as the core methodology for business knowledge networks, with DIP as the core platform, aiming to provide elastic, agile, and reliable enterprise-grade decision intelligence to further unleash productivity. The DIP platform includes key subsystems such as ADP, Decision Agent, DIP Studio, and AI Store.

github

: 154

claudex

Claudex is an open-source, self-hosted Claude Code UI that runs entirely on your machine. It provides multiple sandboxes, allows users to use their own plans, offers a full IDE experience with VS Code in the browser, and is extensible with skills, agents, slash commands, and MCP servers. Users can run AI agents in isolated environments, view and interact with a browser via VNC, switch between multiple AI providers, automate tasks with Celery workers, and enjoy various chat features and preview capabilities. Claudex also supports marketplace plugins, secrets management, integrations like Gmail, and custom instructions. The tool is configured through providers and supports various providers like Anthropic, OpenAI, OpenRouter, and Custom. It has a tech stack consisting of React, FastAPI, Python, PostgreSQL, Celery, Redis, and more.

github

: 197

z.ai2api_python

Z.AI2API Python is a lightweight OpenAI API proxy service that integrates seamlessly with existing applications. It supports the full functionality of GLM-4.5 series models and features high-performance streaming responses, enhanced tool invocation, support for thinking mode, integration with search models, Docker deployment, session isolation for privacy protection, flexible configuration via environment variables, and intelligent upstream model routing.

github

: 210

observers

Observers is a lightweight library for AI observability that provides support for various generative AI APIs and storage backends. It allows users to track interactions with AI models and sync observations to different storage systems. The library supports OpenAI, Hugging Face transformers, AISuite, Litellm, and Docling for document parsing and export. Users can configure different stores such as Hugging Face Datasets, DuckDB, Argilla, and OpenTelemetry to manage and query their observations. Observers is designed to enhance AI model monitoring and observability in a user-friendly manner.

github

: 231

private-llm-qa-bot

This is a production-grade knowledge Q&A chatbot implementation based on AWS services and the LangChain framework, with optimizations at various stages. It supports flexible configuration and plugging of vector models and large language models. The front and back ends are separated, making it easy to integrate with IM tools (such as Feishu).

github

: 262

Agentic-ADK

Agentic ADK is an Agent application development framework launched by Alibaba International AI Business, based on Google-ADK and Ali-LangEngine. It is used for developing, constructing, evaluating, and deploying powerful, flexible, and controllable complex AI Agents. ADK aims to make Agent development simpler and more user-friendly, enabling developers to more easily build, deploy, and orchestrate various Agent applications ranging from simple tasks to complex collaborations.

github

: 508

topsha

LocalTopSH is an AI Agent Framework designed for companies and developers who require 100% on-premise AI agents with data privacy. It supports various OpenAI-compatible LLM backends and offers production-ready security features. The framework allows simple deployment using Docker compose and ensures that data stays within the user's network, providing full control and compliance. With cost-effective scaling options and compatibility in regions with restrictions, LocalTopSH is a versatile solution for deploying AI agents on self-hosted infrastructure.

github

: 81

For similar tasks

superagent-py

Superagent is an open-source framework that enables developers to integrate production-ready AI assistants into any application quickly and easily. It provides a Python SDK for interacting with the Superagent API, allowing developers to create, manage, and invoke AI agents. The SDK simplifies the process of building AI-powered applications, making it accessible to developers of all skill levels.

github

: 99

AGiXT

AGiXT is a dynamic Artificial Intelligence Automation Platform engineered to orchestrate efficient AI instruction management and task execution across a multitude of providers. Our solution infuses adaptive memory handling with a broad spectrum of commands to enhance AI's understanding and responsiveness, leading to improved task completion. The platform's smart features, like Smart Instruct and Smart Chat, seamlessly integrate web search, planning strategies, and conversation continuity, transforming the interaction between users and AI. By leveraging a powerful plugin system that includes web browsing and command execution, AGiXT stands as a versatile bridge between AI models and users. With an expanding roster of AI providers, code evaluation capabilities, comprehensive chain management, and platform interoperability, AGiXT is consistently evolving to drive a multitude of applications, affirming its place at the forefront of AI technology.

github

: 3.1k

infra

E2B Infra is a cloud runtime for AI agents. It provides SDKs and CLI to customize and manage environments and run AI agents in the cloud. The infrastructure is deployed using Terraform and is currently only deployable on GCP. The main components of the infrastructure are the API server, daemon running inside instances (sandboxes), Nomad driver for managing instances (sandboxes), and Nomad driver for building environments (templates).

github

: 660

Awesome-European-Tech

Awesome European Tech is an up-to-date list of recommended European projects and companies curated by the community to support and strengthen the European tech ecosystem. It focuses on privacy and sustainability, showcasing companies that adhere to GDPR compliance and sustainability standards. The project aims to highlight and support European startups and projects excelling in privacy, sustainability, and innovation to contribute to a more diverse, resilient, and interconnected global tech landscape.

github

: 835

LarAgent

LarAgent is a framework designed to simplify the creation and management of AI agents within Laravel projects. It offers an Eloquent-like syntax for creating and managing AI agents, Laravel-style artisan commands, flexible agent configuration, structured output handling, image input support, and extensibility. LarAgent supports multiple chat history storage options, custom tool creation, event system for agent interactions, multiple provider support, and can be used both in Laravel and standalone environments. The framework is constantly evolving to enhance developer experience, improve AI capabilities, enhance security and storage features, and enable advanced integrations like provider fallback system, Laravel Actions integration, and voice chat support.

github

: 78

agent-squad

Agent Squad is a flexible, lightweight open-source framework for orchestrating multiple AI agents to handle complex conversations. It intelligently routes queries, maintains context across interactions, and offers pre-built components for quick deployment. The system allows easy integration of custom agents and conversation messages storage solutions, making it suitable for various applications from simple chatbots to sophisticated AI systems, scaling efficiently.

github

: 6.8k

mcp-gateway-registry

The MCP Gateway & Registry is a unified, enterprise-ready platform that centralizes access to both MCP Servers and AI Agents using the Model Context Protocol (MCP). It serves as a Unified MCP Server Gateway, MCP Servers Registry, and Agent Registry & A2A Communication Hub. The platform integrates with external registries, providing a single control plane for tool access, agent orchestration, and communication patterns. It transforms the chaos of managing individual MCP server configurations into an organized approach with secure, governed access to curated servers and registered agents. The platform supports dynamic tool discovery, autonomous agent communication, and unified policies for server and agent access.

github

: 426

boxlite

github

: 1.0k

For similar jobs

sweep

Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

github

: 7.1k

teams-ai

The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

github

: 502

ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github

: 159

classifai

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

github

: 697

chatbot-ui

Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

github

: 27.7k

BricksLLM

BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

github

: 953

uAgents

uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

github

: 1.3k

griptape

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

github

: 2.2k