void-box

agent
Security Audit
Pass
Health Pass
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 43 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This tool is a composable agent runtime that executes AI-driven tasks and pipelines within strictly isolated micro-VM boundaries. It is designed to run agent capabilities securely by restricting execution environments using policies, seccomp-BPF, and command allowlists.

Security Assessment
Overall Risk: Low
The tool inherently executes commands and makes network requests to pull OCI images and contact AI providers, but it is specifically built around a security-first architecture. It uses strong isolation primitives (micro-VMs, seccomp-BPF) to sandbox these exact actions. A light code audit found no dangerous patterns, hardcoded secrets, or requests for dangerous host permissions. Mounting host directories is a supported feature, but it is explicitly controlled via read-only or read-write parameters, giving the user strict control over data access.

Quality Assessment
The project is actively maintained, with its most recent push happening today. It utilizes the permissive Apache-2.0 license and demonstrates a healthy early-stage community trust with 43 GitHub stars. The codebase is written in Rust, which provides strong memory safety guarantees. The developers indicate it is an early release (v0) with APIs still stabilizing, meaning users should expect potential changes, though the underlying architecture is noted as production-ready. Continuous Integration (CI) is visibly integrated via GitHub Actions.

Verdict
Safe to use. Its core design strictly enforces isolation boundaries for agent execution, making it a highly secure option for running AI pipelines.
SUMMARY

Composable agent runtime with enforced isolation boundaries

README.md
void-box

Void-Box

Composable agent runtime with enforced isolation boundaries

Design principle: Skills are declared capabilities.
Capabilities only exist when bound to an isolated execution boundary.

VoidBox = Agent(Skills) + Isolation

CI License Rust 1.88+

Architecture · Install · Quick Start (CLI · Rust) · OCI Support · Host Mounts · Snapshots · Observability

Local-first. Cloud-ready. Runs on any Linux host with /dev/kvm.

Status: v0 (early release). Production-ready architecture; APIs are still stabilizing.

hn_demo — two-stage stock analysis pipeline


What You Get

  • Isolated execution — Each stage runs inside its own micro-VM boundary, not shared-process containers.
  • Policy-enforced runtime — Command allowlists, resource limits, seccomp-BPF, and controlled network egress.
  • Skill-native model — MCP servers, SKILL files, and CLI tools mounted as declared capabilities.
  • Composable pipelines — Sequential .pipe(), parallel .fan_out(), with explicit stage-level failure domains.
  • Claude Code native runtime — Each stage runs claude-code, backed by Claude or Ollama via provider mode.
  • OCI-native — Auto-pulls guest images from GHCR; mount container images as base OS or skill providers.
  • Observability native — OTLP traces, metrics, structured logs, and stage-level telemetry emitted by design.
  • Persistent host mounts — Share host directories into guest VMs via 9p/virtiofs with read-only or read-write mode.
  • No root required — Usermode SLIRP networking via smoltcp (no TAP devices).

Isolation is the primitive. Pipelines are compositions of bounded execution environments.

Why Not Containers?

Containers share a host kernel — sufficient for general isolation, but AI agents executing tools, code, and external integrations create shared failure domains. VoidBox binds each agent stage to its own micro-VM boundary, enforced by hardware virtualization rather than advisory process controls. See Architecture (source) for the full security model.


Install the voidbox CLI

Each release ships voidbox together with a kernel and initramfs so you can run workloads out of the box.

Shell installer (Linux & macOS)

curl -fsSL https://raw.githubusercontent.com/the-void-ia/void-box/main/scripts/install.sh | sh

Installs to /usr/local/bin and /usr/local/lib/voidbox/. For a specific version: VERSION=v0.1.2 curl -fsSL ... | sh.

Homebrew (macOS)

brew tap the-void-ia/tap
brew install voidbox

Debian / Ubuntu

Download the .deb for your CPU (amd64 or arm64) from Releases. Example for v0.1.2 on amd64:

curl -fsSLO https://github.com/the-void-ia/void-box/releases/download/v0.1.2/voidbox_0.1.2_amd64.deb
sudo dpkg -i voidbox_0.1.2_amd64.deb

Fedora / RHEL

sudo rpm -i https://github.com/the-void-ia/void-box/releases/download/v0.1.2/voidbox-0.1.2-1.x86_64.rpm

Use the matching .rpm name from Releases for your version and architecture.

Next steps

Getting Started First run, environment variables, API keys
Install (site) Copy-paste install block and direct tarball links

If you use Rust already, you can also cargo install void-box for the CLI only — pair it with kernel and initramfs from a release tarball or another install method above.


Quick Start

Using the CLI

With voidbox on your PATH, run an agent from a YAML spec. From a clone of this repository:

voidbox run --file examples/hackernews/hackernews_agent.yaml

CLI overview: voidbox run, validate, inspect, skills, snapshot, and config run locally and do not require a background server. For HTTP remote control, start voidbox serve (default 127.0.0.1:43100), then use status, logs, or tui against that daemon. Full command reference: CLI + TUI.

The full spec lives in examples/hackernews/hackernews_agent.yaml. A minimal shape looks like:

api_version: v1
kind: agent
name: hn_researcher
sandbox:
  mode: auto
  memory_mb: 1024
  network: true
llm:
  provider: claude
agent:
  prompt: "Your task…"
  skills:
    - "file:examples/hackernews/skills/hackernews-api.md"
  timeout_secs: 600

Using the Rust library

Add the crate and build a VoidBox in code:

cargo add void-box
use void_box::agent_box::VoidBox;
use void_box::skill::Skill;
use void_box::llm::LlmProvider;

// Skills = declared capabilities
let hn_api = Skill::file("skills/hackernews-api.md")
    .description("HN API via curl + jq");

let reasoning = Skill::agent("claude-code")
    .description("Autonomous reasoning and code execution");

// VoidBox = Agent(Skills) + Isolation
let researcher = VoidBox::new("hn_researcher")
    .skill(hn_api)
    .skill(reasoning)
    .llm(LlmProvider::ollama("qwen3-coder"))
    .memory_mb(1024)
    .network(true)
    .prompt("Analyze top HN stories for AI engineering trends")
    .build()?;

Documentation

Architecture Component diagram, data flow, security model
Runtime Model Claude Code runtime, LLM providers, skill types
CLI + TUI Command reference, daemon API endpoints
Events + Observability Event types, OTLP traces, metrics
OCI Containers Guest images, base images, OCI skills
Snapshots Sub-second VM restore, snapshot types
Host Mounts 9p/virtiofs host directory sharing
Security Defense in depth, session auth, seccomp
Wire Protocol vsock framing, message types

Guides

Getting Started Install, first agent, first run
Running on Linux KVM setup, manual build, mock mode, tests
Running on macOS Apple Silicon, Virtualization.framework
Observability Setup OTLP config, Grafana playground
AI Agent Sandboxing Isolated micro-VM agent execution
Pipeline Composition Multi-stage pipelines with .pipe() and .fan_out()
YAML Specs Declarative agent/pipeline definitions
Local LLMs Ollama integration via SLIRP networking

Roadmap

VoidBox is evolving toward a durable, capability-bound execution platform.

  • Session persistence — Durable run/session state with pluggable backends (filesystem, SQLite, Valkey).
  • Terminal-native interactive experience — Panel-based, live-streaming interface powered by the event API.
  • Codex-style backend support — Optional execution backend for code-first workflows.
  • Language bindings — Python and Node.js SDKs for daemon-level integration.

License

Apache-2.0 · The Void Platform

Reviews (0)

No results found