Latest

LiteLLM Supply Chain Attack: Defense in Depth Is the Only AI Security Strategy

Show HN: Orloj – agent infrastructure as code (YAML and GitOps)

Hey HN, we&#x27;re Jon and Kristiane, and we&#x27;re building Orloj (<a href="https:&#x2F;&#x2F;orloj.dev" rel="nofollow">https:&#x2F;&#x2F;orloj.dev</a>), an open-source (Apache 2.0) orchestration runtime for multi-agent AI systems. You define agents, tools, policies, and workflows in declarative YAML manifests, and Orloj handles scheduling, execution, governance, and reliability.<p>We built this because running AI agents in production today looks a lot like running containers before Kubernetes: ad-hoc scripts, no governance, no observability, no standard way to manage the lifecycle of an agent fleet. Everyone we talked to was writing the same messy glue code to wire agents together, and nobody had a good answer for &quot;which agent called which tool, and was it supposed to?&quot;<p>Orloj treats agents the way infrastructure-as-code treats cloud resources. You write a manifest that declares an agent&#x27;s model, tools, permissions, and execution limits. You compose agents into direc

AI Arbitrator

Show HN: I built a lawyer game with AI

I&#x27;ve always enjoyed watching legal dramas and courtroom videos. I also started getting curious about courts and law and legal battles well into my adulthood; well into my career as a dev. So I thought &quot;Why not build a game out of it?&quot;<p>Of course, building it became possible only after AI, so here it is! Hope this game helps scratch that lawyer itch we all sometimes have!

China’s CXMT Rides AI Boom to Record Revenue Ahead of IPO

ChangXin Memory Technologies Inc. more than doubled revenue to $8 billion in 2025, giving the strategically important Chinese chipmaker a major boost ahead of one of this year’s biggest domestic IPOs.

Show HN: Prompt Guard–MitM proxy that blocks secrets before they reach AI APIs

I didn't understand TurboQuant, so I made this explainer

Show HN: Agent Kernel – Three Markdown files that make any AI agent stateful

HN: Surviving the litellm supply chain attack with a pure ctypes OS Vault

Research Shows Verbatim Recall of Copyrighted Books in LLMs

TSA boss warns of airport shutdowns; no deal yet on day 40 of DHS funding fight

Gold, a 'safe haven' in uncertain times: Why is it crashing amid a war?

LiteLLM Supply Chain Attack: Defense in Depth Is the Only AI Security Strategy

Show HN: Orloj – agent infrastructure as code (YAML and GitOps)

Hey HN, we&#x27;re Jon and Kristiane, and we&#x27;re building Orloj (<a href="https:&#x2F;&#x2F;orloj.dev" rel="nofollow">https:&#x2F;&#x2F;orloj.dev</a>), an open-source (Apache 2.0) orchestration runtime for multi-agent AI systems. You define agents, tools, policies, and workflows in declarative YAML manifests, and Orloj handles scheduling, execution, governance, and reliability.<p>We built this because running AI agents in production today looks a lot like running containers before Kubernetes: ad-hoc scripts, no governance, no observability, no standard way to manage the lifecycle of an agent fleet. Everyone we talked to was writing the same messy glue code to wire agents together, and nobody had a good answer for &quot;which agent called which tool, and was it supposed to?&quot;<p>Orloj treats agents the way infrastructure-as-code treats cloud resources. You write a manifest that declares an agent&#x27;s model, tools, permissions, and execution limits. You compose agents into direc

AI Arbitrator

Show HN: I built a lawyer game with AI

I&#x27;ve always enjoyed watching legal dramas and courtroom videos. I also started getting curious about courts and law and legal battles well into my adulthood; well into my career as a dev. So I thought &quot;Why not build a game out of it?&quot;<p>Of course, building it became possible only after AI, so here it is! Hope this game helps scratch that lawyer itch we all sometimes have!