AgentBox – SDK to Run Claude Code, Codex, or OpenCode in Any Sandbox
AgentBox – SDK to Run Claude Code, Codex, or OpenCode in Any Sandbox
Hi HN, AgentBox is an SDK for running coding agents (Claude Code, Codex, OpenCode) inside sandboxes (Docker, E2B, Modal, Daytona, Vercel). One API. Swap the agent or the sandbox and your code doesn't change. Think of it as what the AI SDK did for LLMs, but for agent + runtime. Most wrappers call agents in non interactive mode (claude --print, codex exec). AgentBox instead boots each agent's native server inside the sandbox (Codex app-server over JSON-RPC, OpenCode serve over HTTP/SSE, Claude Code's SDK WebSocket transport) and drives it from the host, behaving like an interactive session. Live demo: https://agentbox-demo-175164121374.us-west1.run.app Feedback welcome, especially on the abstractions and which providers to add next!
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Incorrect prediction on native model
Similar products
Run Claude Code, Codex or Opencode in cloud with your repo
Run Claude Code and Codex in the cloud
Run Claude Code, Codex & Gemini in one desktop cockpit
Sandbox claude code, codex, or any TUI on macOS
Castforge – run Claude Code, Codex and Gemini as one dev team
Run Claude Code and Codex anywhere, on any device
Run an army of Claude Code, Codex, etc. on your machine
Cetus – A macOS App for Claude Code, Codex, OpenCode, and More
Run Claude Code and Codex in your own cloud environment
Agentpack – isolated config layers for Claude Code, Codex, and OpenCode