一个让LLM代理在V8沙箱中执行TypeScript的开源安全运行时，策略引擎自动批准升级，但安全标签需谨慎。
Article URL: https://github.com/provos/ironcurtain Comments URL: https://news.ycombinator.com/item?id=48902269 Points: 1 # Comments: 0
Python运行时，让多个agent智能协作完成分布式任务，开源且轻量。
Article URL: https://github.com/nMaroulis/protolink Comments URL: https://news.ycombinator.com/item?id=48892091 Points: 2 # Comments: 0
Claude Fable 5 只用11天生成超100万行Rust代码，高效重构JavaScript运行时Bun，AI编程能力惊人。
IT之家 7 月 11 日消息，开发者贾里德 · 萨姆纳（Jarred Sumner）于 7 月 8 日发布博文，宣布在 Claude Fable 5 模型的帮助下，耗时 11 天、耗费 16.5 万美元， 已重构 JavaScript 运行时 Bun，从 Zig 完全重写为 Rust 语言。 萨姆…
提出Token流语义防火墙，为持久AI代理提供运行时审计，保障Agent安全。
arXiv:2607.08395v1 Announce Type: cross Abstract: Persistent AI agents extend large language models (LLMs) beyond single-turn interaction into long-li…
扔掉Transformer和显卡，纯CPU拓扑AI架构让LLM高效运行，开源方案值得关注。
Article URL: https://www.hackster.io/jenfi59/brainiak-topological-al-drives-llm-by-lora-runtime-adapters-73a678 Comments URL: https://news.ycombinator…
1-bit量化+WebGPU，让1.7B大模型在浏览器里流畅运行，技术突破值得关注。
Article URL: https://aidekin.com/ Comments URL: https://news.ycombinator.com/item?id=48820583 Points: 4 # Comments: 2
开源且支持500+模型的AI Agent防火墙，基于OWASP Top 10安全规则，内置W3C OTLP追踪与EU AI Act合规。
Article URL: https://github.com/CURSED-ME/loopers-oss Comments URL: https://news.ycombinator.com/item?id=48804865 Points: 1 # Comments: 0
探索如何将网络故障降级为传输事件而非会话死亡，一套打破常规的连续性运行时架构思路。
GitHub - Endless33/jumping-vpn-preview · GitHub Contribute to Endless33/jumping-vpn-preview development by creating an account on GitHub. github.com
提出认证推测执行框架，用形式化证明保障不可信AI智能体在运行时的安全性，兼顾效率与可证明保证
arXiv:2606.31023v1 Announce Type: cross Abstract: Hard-constrained sequential decision systems have no certified way to spend the test-time compute of…
CaveAgent突破传统无状态LLM限制，打造有状态运行时操作器，为智能体注入持久记忆。
arXiv:2601.01569v4 Announce Type: replace Abstract: LLM-based agents are increasingly capable of complex task execution, yet current agentic systems r…
专为AI代理设计的消息运行时，解决传统聊天工具不适配问题，独立创始人诚意之作。
I'm a solo founder building AMA2, a messaging runtime made for AI agents. This is my first Show HN, so I'd really appreciate your feedback. What broug…
LLM不再是辅助工具，而是直接作为CPU运行代码的创新编译器架构，重新定义冯·诺依曼机。
Article URL: https://aicompiler.dev Comments URL: https://news.ycombinator.com/item?id=48718031 Points: 2 # Comments: 0
2行代码即可为AI代理设置运行时预算，实时监控消耗，防止失控浪费。
Hi HN, I’m a solo developer and built AgentWatch to solve a problem I kept running into while building AI agents: preventing runaway loops and unexpec…
研究发现AI编码代理的提交遥测严重低估了真实使用量，运行时遥测揭示30倍的数据缺口。
A new arXiv paper published on June 23, 2026 scanned more than 180 million Git repositories to detect traces of AI coding agents in open source. The a…
用道义策略实时管控AI行为体行为，确保符合规范与伦理。
arXiv:2606.19464v1 Announce Type: new Abstract: Autonomous agentic AI systems driven by Large Language Models (LLMs) introduce a new class of security…
浏览器原生终端Ghostty+完整客户端后端，WebAssembly跑Bash/Git，无需服务器即可体验终端环境
A real work in progress I've got here. Our good friend Ghostty is now haunting the browser. Ghostty Playground is an experimental project based on gho…
历时八个月生产环境实证，揭示LLM agent运行时中40+类静默失败的演化规律
arXiv:2606.14589v1 Announce Type: cross Abstract: LLM agent systems increasingly run as long-lived autonomous runtimes: scheduling jobs, calling tools…
Rust打造的能力沙箱化JS/TS运行时，单一自包含二进制，无需额外依赖库，安全又轻量。
Hey everyone! I've been working on something called Afterburner: a fast, embeddable JS/TS runtime written in Rust, with a capability sandbox baked rig…
AI代理运行时防跑飞利器，集中管理预算限制，告别分散检查。
Article URL: https://guard-sdk.js.org/ Comments URL: https://news.ycombinator.com/item?id=48466595 Points: 1 # Comments: 0
在运行Claude Code时实时拦截API调用，防止token过度消耗与密钥意外泄露，守护你的钱包与安全。
Article URL: https://github.com/ashp15205/guardian-runtime Comments URL: https://news.ycombinator.com/item?id=48464199 Points: 2 # Comments: 0