开源AI编程智能体加固沙箱Lyngvi发布v2.0.0版本
Start here
2026年11月3日，开源安全沙箱Lyngvi正式发布v2.0.0版本，旨在为自主编程智能体提供基于Podman的系统加固执行环境，同时支持桌面应用与命令行驱动。在安全机制方面，该方案通过独立容器隔离会话，切断直连外网路由，并由代理强制执行出站域名黑白名单，敏感凭证则由网关Sidecar单向注入。此外，智能体仅能在剥离历史记录的工作副本中进行操作，所生成的文件变更必须经过机器分类与人工审核后，才能提交至开发分支。
AI-generated from reports · Updated 11 hours ago
Report timeline
Follow the reports to see different sides of the story.
- Hacker News · AISelectedLyngvi v2.0.0 Released: Hardened Sandbox for AI Coding Agents
Open-source security sandbox Lyngvi has released v2.0.0, offering a Podman-based hardened execution environment for autonomous coding agents with support for both desktop applications and CLI workflows. The solution isolates sessions within dedicated containers, cuts off direct outbound internet routing while enforcing domain allowlists and blocklists via an egress proxy, and injects credentials unidirectionally through a gateway sidecar. Agents operate exclusively inside working copies stripped of Git history, and any generated file changes must undergo automated triage and human review before being committed to development branches.
Story heat trend
Current heat 7·Comparable peak 10（Nov 3 06:00）·Comparable change, last 24 hours–
Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.