TencentCloud/CubeSandbox
Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
5 releases in the last 90 days, the latest 23 days ago, with 118 contributors on GitHub.
Peaked at #12 in the weekly ranking the week of Sep 13, its best in the past year.
Use Cases & Benefits
- Provides an instant, concurrent, secure, and lightweight sandbox service for AI agents using hardware-level isolation and KVM virtualization.
- Delivers sub-60ms cold start times with ultra-low memory overhead under 5MB, enabling high-density deployment of thousands of sandboxes per node.
- Use for securely running untrusted AI-generated code with strong kernel-level isolation to prevent container escape risks.
- Use for scalable multi-node cluster deployments requiring fast sandbox provisioning and event-level snapshot rollback for state management.
- Use for migrating from closed-source sandboxes to an open-source, E2B-compatible solution without changing existing business logic.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Other
GitHub could not identify this license; read the LICENSE file before depending on it.
Community files
- README: present
- Contributing guide: present
Watch-outs
- License not identified by GitHub; read the LICENSE file before depending on it.
General guidance from repository metadata, not legal advice. How we score
From the README
Instant, Concurrent, Secure & Lightweight Sandbox Service for AI Agents
Cube Sandbox is a high-performance, out-of-the-box secure sandbox service built on RustVMM and KVM. It supports both single-node deployment and easy scaling to multi-node clusters. It is compatible with the E2B SDK and can create a hardware-isolated, fully serviceable sandbox in under 60ms with less than 5MB of memory overhead.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+2,190 stars over 90 days across 30 snapshot days; best day +111 on Sep 17.
Forks
1.2K+185
Open issues
222+93
Compared with peers in Backend
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| anthropics/skills | 192.3K | +5.2K | 75 | — |
| zed-industries/zed | 94.7K | +2.3K | 75 | 6 days ago |
| google/skills | 23.8K | +2.0K | 75 | — |
| NationalSecurityAgency/ghidra | 99.4K | +1.8K | 75 | 19 days ago |
| DuarteSantos8/openGym | 20.8K | +1.7K | 75 | 7 days ago |
| TencentCloud/CubeSandbox | 13.2K | — | 59 | 23 days ago |
| Category median | 94.7K | +2.0K | 75 | — |
Also by TencentCloud
Other repositories from this maintainer that GStars tracks
- TypeScript30.3K stars
TencentDB-Agent-Memory
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.
- Python11.8K stars
Octop
A smarter, self-hosted AI assistant — multi-user, multi-agent.
Discover Repositories
Search across tracked repositories by name or description