# opensandbox-group/OpenSandbox

> Sandbox runtime for AI agents that runs code, commands, files, browsers and desktops in isolated environments, locally on Docker or on Kubernetes via a unified API. An Agentic AI Foundation project.

- Magnitude: 6.9 out of 10 — Breakout
- Stars: 17,004 total · +85 stars measured 2026-11-10, 00:26–06:03 UTC, ≈ 308 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2025-12-17 · Last push: 2026-11-10
- GitHub: https://github.com/opensandbox-group/OpenSandbox · Homepage: https://open-sandbox.ai · Page: https://gitnova.dev/en/r/opensandbox-group/OpenSandbox

## Useful for

- Run a coding agent in an isolated sandbox to edit files and execute commands
- Execute model-generated code in a sandbox via the Code Interpreter SDK
- Connect sandboxes to Claude Code or Cursor through the MCP server

## How to get started

```sh
uvx opensandbox-server init-config ~/.sandbox.toml --example docker

uvx opensandbox-server

# Show help
# uvx opensandbox-server -h
```

Copied as is from the “getting started” section of the README. GitNova has not run these commands: check them in the original before running: https://github.com/opensandbox-group/OpenSandbox#readme

## Why it’s here

- Star-counter measurements on 2026-11-10 (UTC), 00:26–06:03: 16919 → 17004 stars (+85). This is the change over that interval.
- Estimated end-of-day forecast: about +308 stars, using observed gains and the previous day.
- Over the last two days the pace is 10× that of the previous week and a half.
- Elevated gains were measured on the last 2 completed UTC days in a row. Continued growth is not guaranteed.
- GitHub Trending Python today: #14, +168 stars.
- About 51 forks a day — people are taking the code.
- Recent forks include notable developers: @rudycelekli (770 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1,604
- Issues and pull requests: 2,666
- Watchers: 61
- Average over the last week: 127 per day
- Usual pace: 30 per day
- Stars in the last hour (measured): 17
- Latest release: release-1.2.1-rc.1 (2026-11-04)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-12 … 2026-11-10: 26, 26, 24, 24, 25, 21, 28, 27, 22, 28, 37, 41, 30, 29, 27, 31, 21, 36, 43, 29, 27, 40, 22, 23, 16, 18, 54, 175, 292, 85

## Magnitude by day, last 2 days

11-09 5.4, 11-10 6.9

## Spotted in now

- GitHub Trending Python today: #14, +168 stars

## Similar by description

1. **pydantic/monty** — 1.5 · Steady · AI agents · Rust · +1 star measured 2026-11-10, 00:32–06:09 UTC, ≈ 8 by evening
   A minimal, secure Python interpreter written in Rust for running code generated by AI models without containers or VMs. It isolates filesystem, network and environment variables, and enforces memory, time and recursion limits.
   Full card: https://gitnova.dev/en/r/pydantic/monty.md
2. **orkbot-run/ork** — 0.0 · Cooling · AI agents · TypeScript · Not enough measurements today
   Source-available AI assistant with persistent bots that share conversations and run on isolated computers; self-hosted, with web, desktop, and mobile clients.
   Full card: https://gitnova.dev/en/r/orkbot-run/ork.md
3. **joesecurity/joesandboxMCP** — 0.0 · Quiet · Python · Not enough measurements today
   MCP for Joe Sandbox Cloud
   Full card: https://gitnova.dev/en/r/joesecurity/joesandboxMCP.md
4. **google/ax** — 1.5 · Cooling · AI agents · Go · +2 stars measured 2026-11-10, 00:32–06:09 UTC, ≈ 9 by evening
   A declarative orchestrator for running autonomous AI agent workloads in a cluster, using a Kubernetes-like model with Task, Workspace, Gateway, and Model manifests. It sandboxes agents, pre-wires their environment, and restricts network…
   Full card: https://gitnova.dev/en/r/google/ax.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-10 06:13 UTC, updated every 30 minutes.