@nash_su: Last night I was chatting with @i5ting about how a sandbox is an indispensable part of any agent, and today Tencent open-sourced Cube Sandbox: 1. Blazing-fast boot (<60 ms) thanks to snapshot cloning and warm resource pools 2. Hardware-grade security via KVM micro-VMs + eBPF network isolation, battle-tested on Tencent Cloud 3. Ultra-high density—runs in <5 MB RAM, thousands per node 4. E2B-compatible
Summary
Tencent open-sources Cube Sandbox, a KVM-based micro-VM for agents that boots in <60 ms, runs in <5 MB RAM, and is E2B-compatible.
View Cached Full Text
Cached at: 04/23/26, 10:00 AM
Just last night I was chatting with @i5ting about how a sandbox is an indispensable part of any agent, and today Tencent open-sourced this Cube Sandbox:
- Blazing-fast boot (< 60 ms) — thanks to snapshot cloning and resource-pool pre-warming
- Hardware-grade security — KVM micro-VM + eBPF network isolation, battle-tested on Tencent Cloud
- Ultra-high density — < 5 MB RAM per instance, thousands on a single node
- E2B compatible
Similar Articles
TencentCloud/CubeSandbox
TencentCloud's CubeSandbox is an open-source, high-performance secure sandbox service for AI agents, built on RustVMM and KVM, offering hardware-level isolation, sub-60ms startup, and compatibility with the E2B SDK.
@TencentAI_News: We just open-sourced Cube Sandbox! An instant, concurrent, secure and lightweight sandbox runtime for AI Agents. Built …
Tencent open-sourced Cube Sandbox, a lightweight Rust/KVM-based sandbox runtime for AI agents that cold-starts in under 60 ms with <5 MB overhead.
@ErickSky: TENCENT JUST DROPPED THE BOMB for everyone making AI Agents: A sandbox that: - Starts in under 60 ms (up to 50x faster)…
Tencent released an ultra-lightweight sandbox for AI agents that starts in <60 ms, uses 5 MB RAM, supports 2000+ instances per server, and offers KVM-based security.
Tencent Cloud open-sources Cube Sandbox, an AI-agent sandbox written in Rust under Apache 2.0
Tencent Cloud’s Rust-based Cube Sandbox offers an E2B-compatible, isolated runtime for LLM-generated code.
@vintcessun: Found a new approach: coding agent can be this lightweight. 16MB memory, 0% idle CPU, 26MB binary — these numbers are insane in the agent space. It's built with Rust, packing all standard tools, permission system, session management, and MCP into 17k LoC...
Zerostack is a minimal coding agent written in Rust, consuming only 16MB of memory and a 26MB binary. It achieves lightweight design through feature gates, supporting multiple providers and tools.