惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

云风的 BLOG
云风的 BLOG
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
IT之家
IT之家
Recent Announcements
Recent Announcements
B
Blog
D
Docker
V
V2EX
GbyAI
GbyAI
L
LangChain Blog
博客园 - Franky
U
Unit 42
T
The Blog of Author Tim Ferriss
A
About on SuperTechFans
博客园 - 【当耐特】
Google DeepMind News
Google DeepMind News
H
Hackread – Cybersecurity News, Data Breaches, AI and More
Vercel News
Vercel News
博客园_首页
D
DataBreaches.Net
人人都是产品经理
人人都是产品经理
Y
Y Combinator Blog
量子位
Blog — PlanetScale
Blog — PlanetScale
罗磊的独立博客

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
GitHub - boxlite-ai/boxlite: Sandboxes for every agent. E...
dorianzheng · 2026-05-03 · via Hacker News: Show HN

GitHub stars Build Lint codecov License

Local-first micro-VM sandbox for AI agents — stateful, lightweight, hardware-level isolation, no daemon required.

What is BoxLite?

BoxLite lets you spin up lightweight VMs ("Boxes") and run OCI containers inside them. Unlike ephemeral sandboxes that destroy state after each execution, BoxLite Boxes are persistent workspaces — install packages, create files, build up environment state, then come back later and pick up where you left off.

Why BoxLite

  • Stateful: Boxes retain packages, files, and environment across stop/restart. No rebuilding on every interaction.
  • Lightweight: small footprint, fast boot, async-first API for high concurrency.
  • Hardware isolation: each Box runs its own kernel — not just namespaces or containers.
  • No daemon: embed as a library, no root, no background service.
  • OCI compatible: use standard Docker images (python:slim, node:alpine, alpine:latest).
  • Network policy + secret placeholders: restrict outbound access with allow_net and inject real HTTP(S) secrets from host-side secrets.
  • Local-first: runs entirely on your machine — no cloud account needed. Scale out when ready.

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

cargo add 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(())
}

Go Quick Start

View guide

Install

go get github.com/boxlite-ai/boxlite/sdks/go
go run github.com/boxlite-ai/boxlite/sdks/go/cmd/setup

Requires Go 1.24+ with CGO enabled. The setup step downloads the prebuilt native library (one-time).

Run

package main

import (
	"context"
	"fmt"
	"log"

	boxlite "github.com/boxlite-ai/boxlite/sdks/go"
)

func main() {
	rt, err := boxlite.NewRuntime()
	if err != nil {
		log.Fatal(err)
	}
	defer rt.Close()

	ctx := context.Background()
	box, err := rt.Create(ctx, "alpine:latest", boxlite.WithName("my-box"))
	if err != nil {
		log.Fatal(err)
	}
	defer box.Close()

	result, err := box.Exec(ctx, "echo", "Hello from BoxLite!")
	if err != nil {
		log.Fatal(err)
	}
	fmt.Print(result.Stdout)
}

REST API Quick Start

View guide

Install

cargo install boxlite-cli

Start the server

boxlite serve
# Listening on 0.0.0.0:8100

Use it

# Create a box
curl -s -X POST http://localhost:8100/v1/default/boxes \
  -H 'Content-Type: application/json' \
  -d '{"image": "alpine:latest"}'

# Run a command (replace BOX_ID from the response above)
curl -s -X POST http://localhost:8100/v1/default/boxes/BOX_ID/exec \
  -H 'Content-Type: application/json' \
  -d '{"command": "echo", "args": ["Hello from BoxLite!"]}'

All CLI commands also work against a running server:

boxlite --url http://localhost:8100 list
boxlite --url http://localhost:8100 exec BOX_ID -- echo "Hello!"

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: Rust (Rust 1.88+), Python (Python 3.10+), C (C11-compatible compiler), Node.js (Node.js 18+), Go (Go 1.24+)
  • REST API: built-in HTTP server (boxlite serve) — use BoxLite from any language or tool via curl

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) 🚀 Coming soon

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

Getting Help

Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

License

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