#55th of 10 in Sandboxes

opensandbox

Sandbox API for running AI agent code, commands and browsers in isolation

Stars
16k
License
Apache-2.0
Last commit
Oct 2026
Last release
Oct 2026
Language
Python
Stars, last 29 weeks+6,548
31 Mar 2026: 9,466 stars7 Apr 2026: 9,649 stars14 Apr 2026: 9,855 stars21 Apr 2026: 10,014 stars28 Apr 2026: 10,215 stars5 May 2026: 10,311 stars12 May 2026: 10,468 stars19 May 2026: 10,598 stars26 May 2026: 10,727 stars2 Jun 2026: 10,859 stars9 Jun 2026: 11,326 stars16 Jun 2026: 11,455 stars23 Jun 2026: 11,540 stars30 Jun 2026: 11,657 stars7 Jul 2026: 11,808 stars14 Jul 2026: 11,929 stars21 Jul 2026: 12,043 stars28 Jul 2026: 12,171 stars4 Aug 2026: 12,294 stars11 Aug 2026: 12,438 stars18 Aug 2026: 14,239 stars25 Aug 2026: 14,667 stars1 Sept 2026: 14,863 stars8 Sept 2026: 15,028 stars15 Sept 2026: 15,298 stars22 Sept 2026: 15,452 stars29 Sept 2026: 15,584 stars6 Oct 2026: 15,698 stars13 Oct 2026: 15,842 stars20 Oct 2026: 16,014 stars

9,466 on 31 Mar 202616,014 on 20 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

OpenSandbox provides isolated environments where agents execute code, run shell commands, manage files and drive browsers or desktops, through a single lifecycle API. It runs locally on Docker and scales to Kubernetes, with SDKs for Python, Java/Kotlin, TypeScript, C#/.NET and Go, plus an `osb` CLI and an MCP server. Egress policies, an ingress gateway and a credential vault control network access.

Who it is for: Engineers needing isolated code execution for agents on their own infrastructure

Strengths

  • SDKs in five languages plus osb CLI and MCP server
  • Same lifecycle API for local Docker and Kubernetes deployments
  • Per-sandbox egress policies and a credential vault keep real secrets out of workloads
  • Firecracker runtime with pause/resume; reported 64 ms P50 creation time

Weaknesses

  • Docker required for local use; Kubernetes setup needed for the fast runtime
  • No hosted demo or playground listed in the README
  • Firecracker and pause/resume features documented only for the Kubernetes fast runtime
  • Server needs separate install and TOML configuration before first use

What it needs

  • no GPU
  • Needs Docker, Python 3.10+, Kubernetes (optional, for cluster deployment)

Also in Sandboxes

See all 10
Also in Sandboxes
RankProjectScore
1LightpandaHeadless browser written in Zig for agents and scraping, with CDP and MCP36.8k starsAGPL-3.079 out of 100
2ObscuraRust headless browser with V8 and CDP for scraping and agents29.1k starsApache-2.074 out of 100
3OpenShellPolicy-enforced sandbox runtime for autonomous AI agents Live demo ↗ (opens in a new tab)16.9k starsApache-2.073 out of 100
#4NemoClawReference stack for running OpenClaw, Hermes and Deep Agents in OpenShell sandboxes22.8k starsApache-2.072 out of 100
#6cubesandboxMicroVM sandbox service for AI agents with an E2B-compatible API13k starscustom license65 out of 100