7 agents tracked · Open-source-first, with limited public GitHub comparators · Ranked by trust score · Updated 2026-07-15 03:00 UTC
HVTracker independently evaluates 7 sandboxes & runtimes using daily signals from GitHub, package registries, and security databases. The category is open-source-first, with a limited set of public GitHub-hosted proprietary or source-available comparators when they are important ecosystem reference points. Each agent is scored on activity, adoption, transparency, safety, and identity. The top-ranked sandboxes & runtimes is E2B with a trust score of 76.8/100 (Grade B). Other leading projects include BoxLite and Daytona.
| # | Agent | Trust | Stars | Language |
|---|---|---|---|---|
| 1 | E2B B Listed Open-source, secure environment with real-world tools for enterprise-grade agents. | 76.8 | 13.0k | Python |
| 2 | BoxLite B Listed The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud. | 74.8 | 2.2k | Rust |
| 3 | Daytona B Listed Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code | 70.8 | 72.2k | TypeScript |
| 4 | OpenSandbox D Listed Secure, Fast, and Extensible Sandbox runtime for AI agents. | 25.9 | 12.0k | Python |
| 5 | Cube Sandbox D Listed Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents. | 24.9 | 10.2k | Rust |
| 6 | Container Use D Listed Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred | 23.4 | 3.9k | Go |
| 7 | OpenShell D Listed OpenShell is the safe, private runtime for autonomous AI agents. | 19.3 | 7.7k | Rust |