Sandboxes & Runtimes
11 agents tracked · ranked by trust score · Updated 2026-10-13 11:40 UTC · the three strongest right now:
| # | Agent | Trust | Stars | Language |
|---|---|---|---|---|
| 1 | BoxLite A Listed The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud. | 85.1 | 2.5k | TypeScript |
| 2 | E2B B Listed Open-source, secure environment with real-world tools for enterprise-grade agents. | 77.6 | 14.3k | Python |
| 3 | OpenShell B Listed OpenShell is the safe, private runtime for autonomous AI agents. | 74.1 | 16.0k | Rust |
| 4 | Cube Sandbox B Listed Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents. | 71.8 | 12.9k | Go |
| 5 | OpenSandbox B Listed Secure, Fast, and Extensible Sandbox runtime for AI agents. | 70.8 | 15.8k | Python |
| 6 | Fence C Listed Lightweight, container-free sandbox for running commands with network and filesystem restrictions | 56.6 | 991 | Go |
| 7 | Container Use C Listed Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack. | 55.5 | 4.1k | Go |
| 8 | Daytona C Needs review Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code | 53.8 | 71.6k | — |
| 9 | Agent Infra Sandbox C Listed All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container. | 53.2 | 6.1k | Python |
| 10 | Rivet Agents C Listed A durable process per agent, with memory that survives restarts | 52.7 | 1.6k | TypeScript |
| 11 | Zeroboot D Listed Sub-millisecond VM sandboxes for AI agents via copy-on-write forking | 33.5 | 2.5k | Rust |
Grade = trust band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50 — methodology
About Sandboxes & Runtimes
HVTracker independently evaluates 11 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 & runtime is BoxLite with a trust score of 85.1/100 (Grade A). Other leading projects include E2B and OpenShell.