arcboxlabs/arcbox

This page introduces an external open-source repository. It is not an HDATF product.

What it does

ArcBox is an open-source container and VM runtime for macOS written in Rust. It runs Docker-compatible containers, disposable microVM sandboxes for AI agents, and full Linux or macOS VMs on one runtime.

How it helps ATF

Its disposable microVM sandboxes for AI agents and untrusted code are worth comparing as a way to isolate the environment where Harness hands work to executors such as Claude Code or Codex.

License

Apache-2.0 Permissive, with a patent grant. Commercial use is allowed; keep the notices and state your changes.

More in this category

• google/artemis
  ARTEMIS turns natural-language instructions into automation on real or emulated Android devices. Through MCP, coding assistants such as Claude Code can drive test devices and collect logs and screenshots.
• sapientinc/PRAXIST
  An autonomous research system for measurable, computer-executable research. It coordinates parallel research peers, lets each task own its evaluation, keeps durable evidence and carries synthesis from one generation of work to the next.
• EvoMap/AutoResearch
  An agent workflow for AI and machine learning research, from an idea through experiment planning, execution, result analysis and independent review. Plans, code, logs, metrics and review reports are saved to disk so researchers can take over.
• openJiuwen-ai/jiuwenswarm
  A multi-agent system where a leader agent splits complex tasks across teammate agents, including scripted multi-stage workflows with human checkpoints. Skills are revised automatically from error signals, and it is reachable from a browser, terminal or chat apps.
• jmiao24/Paper2Agent
  A multi-agent system that turns a research paper, along with its code repository if available, into an interactive AI agent. It coordinates parallel specialist agents to produce MCP servers and skills.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.