alibaba/OpenSandbox
Secure, Fast, and Extensible Sandbox runtime for AI agents.
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
Secure, Fast, and Extensible Sandbox runtime for AI agents.
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets, and OKX read-only security checks.
🧱 secure, local and programmable sandboxes for AI agents
A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.
Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.
3 captures since 2026-05-23
package.json
· javascript · 3 dependencies
pnpm-lock.yaml
· javascript · 502 dependencies
evaluation/pyproject.toml
· python · 2 dependencies
website/package.json
· javascript · 17 dependencies
evaluation/uv.lock
· python · 37 dependencies
examples/_template/pyproject.toml
· python · 2 dependencies
examples/ag2-integration/pyproject.toml
· python · 3 dependencies
examples/basic-file-operations/pyproject.toml
· python · 2 dependencies
examples/browser-use-cua/pyproject.toml
· python · 3 dependencies
examples/browser-use-integration/pyproject.toml
· python · 3 dependencies
AI agent config detected
Key config paths
website/docs/en/examples/agent.md
website/docs/zh/examples/agent.md