展示HN：EdgeAI-OS – 一种隔离网络的Linux发行版，其中AI作为系统原语。
我构建了一个可启动的Linux发行版，将人工智能视为系统原语——就像CPU或内存一样。该系统专为数据不能离开网络的安全敏感环境设计。
问题：大多数人工智能需要云API，这意味着您的数据将失去控制。对于银行、医疗、国防和受监管行业来说，这根本不可行。
解决方案：EdgeAI-OS在本地运行所有内容。没有云调用，没有API密钥，没有遥测。启动ISO，使用人工智能。您的数据永远不会离开机器。
安全特性：
- 100%离线操作——适合空气隔离，零网络依赖
- 无外部API调用——所有推理在CPU上本地运行
- 命令风险评估——每个命令被分类为安全/中等/危险
- 危险模式阻止——防止执行rm -rf /、curl|bash、fork炸弹等
- 开源且可审计——MIT许可证，检查每一行代码
- 无数据外泄——绝不向外发送任何信息
ISO中包含的内容：
- 本地LLM（TinyLlama 1.1B + SmolLM 135M）——在CPU上运行，无需GPU
- ai-sh：自然语言命令行，80%的查询通过模板瞬间解决
- 多层路由：简单查询→快速模型，复杂查询→更大模型
示例ai-sh会话：
现在几点了？
[模板] date ← 即时，无需LLM
文件大于1GB
[模板] find . -size +1G ← 即时，无需LLM
rm -rf /
[危险] 被阻止 ← 安全检查
将nginx配置为反向代理
[ai生成] ... ← 使用本地LLM（约1-2秒）
目标使用案例：
- 空气隔离的企业环境（银行、医疗、政府）
- 国防与机密网络
- 无互联网连接的边缘设备
- 注重隐私的开发者
- 合规要求高的行业（HIPAA、GDPR、SOC2）
基于Rust构建，基于Debian。推荐4GB RAM。
GitHub: [https://github.com/neuralweaves/edgeai-os](https://github.com/neuralweaves/edgeai-os)
ISO下载: [https://github.com/neuralweaves/edgeai-os/releases](https://github.com/neuralweaves/edgeai-os/releases)（1.2GB）
非常希望获得反馈，尤其是来自安全/受监管环境工作的人员。哪些功能会让您觉得这个系统适合企业使用？
查看原文
I built a bootable Linux distribution that treats AI as a system primitive – like CPU or memory. Designed for security-conscious environments where data cannot leave the network.<p>The problem: Most AI requires cloud APIs, which means your data leaves your control. For banks, healthcare, defense, and regulated industries – that's a non-starter.<p>The solution: EdgeAI-OS runs everything locally. No cloud calls. No API keys. No telemetry. Boot the ISO, use AI. Your data never leaves the machine.<p>Security features:
- 100% offline operation – air-gap friendly, zero network dependencies
- No external API calls – all inference runs locally on CPU
- Command risk assessment – every command classified as Safe/Moderate/Dangerous
- Dangerous pattern blocking – prevents rm -rf /, curl|bash, fork bombs, etc.
- Open source & auditable – MIT licensed, inspect every line of code
- No data exfiltration – nothing phones home, ever<p>What's in the ISO:
- Local LLMs (TinyLlama 1.1B + SmolLM 135M) – runs on CPU, no GPU needed
- ai-sh: natural language shell where 80% of queries resolve instantly via templates
- Multi-tier routing: simple queries → fast model, complex → larger model<p>Example ai-sh session:
what time is it?
[template] date ← instant, no LLM<p>files larger than 1gb
[template] find . -size +1G ← instant, no LLM<p>rm -rf /
[DANGEROUS] Blocked ← security check<p>configure nginx as reverse proxy
[ai-generated] ... ← uses local LLM (~1-2s)<p>Target use cases:
- Air-gapped enterprise environments (banks, healthcare, government)
- Defense & classified networks
- Edge devices with no internet connectivity
- Privacy-conscious developers
- Compliance-heavy industries (HIPAA, GDPR, SOC2)<p>Built with Rust, based on Debian. 4GB RAM recommended.<p>GitHub: <a href="https://github.com/neuralweaves/edgeai-os" rel="nofollow">https://github.com/neuralweaves/edgeai-os</a>
ISO Download: <a href="https://github.com/neuralweaves/edgeai-os/releases" rel="nofollow">https://github.com/neuralweaves/edgeai-os/releases</a> (1.2GB)<p>Would love feedback, especially from anyone working in secure/regulated environments. What features would make this enterprise-ready for you?