Agent Infra Sandbox vs Fence
Fence leads on trust: 56.4/100 (Grade C) against 47.8/100 (Grade D), a 8.6-point gap. Agent Infra Sandbox leads on adoption; Fence leads on supply-chain integrity and maintenance.
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
Choose Agent Infra Sandbox if adoption matters most.
- +1.9Adoption: 6.4k GitHub stars against 1k
Lightweight, container-free sandbox for running commands with network and filesystem restrictions
Choose Fence if supply-chain integrity and maintenance matter most.
- +4.3Maintenance: last push 5d ago, against 69d ago
- +3.0Safety / Integrity: OSSF Scorecard 6.8 against 4.2
- +2.2Transparency: OSSF Scorecard 6.8 against 4.2
Where they differ
1 dimension identical: Identity 10.8 · Full evidence table
An independent, evidence-based trust comparison of Agent Infra Sandbox and Fence, two Sandboxes & Runtimes projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | Agent Infra Sandboxagent-infra/sandbox | Fencefencesandbox/fence |
|---|---|---|
| HVTrust score | 47.8 | 56.4 |
| Evidence grade | D | C |
| Coverage grade | C | C |
| Overall rank | #1073 | #818 |
| Rank in Sandboxes & Runtimes | #11 | #7 |
| GitHub stars | 6.4k | 1.0k |
| Last updated | 69d ago | 5d ago |
| Build provenance | No | No |
| OSSF Scorecard | 4.2 / 10 | 6.8 / 10 |
| License | Apache-2.0 | Apache-2.0 |
| Downloads | — | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 9.4 | 12.4 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 12.1 | 14.3 |
| Maintenance / 20 | 7.4 | 11.7 |
| Adoption / 20 | 9.1 | 7.2 |
| Runtime capability surface (full matrix) | ||
| MCP server | Declared | — |
| External providers | 1 — OpenAI | — |
| Requires API keys | Yes | No |
| Plugin surface | — | — |
| Provenance drift | — | — |
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →