Agent-101-safety-layer

What it does

Most agent safety failures aren't exotic attacks — they're the same dozen mistakes repeated across projects. This book skips the AI research jargon and focuses purely on engineering: permissions, approvals, rate limiting, sandboxing, and audit trails for LLM agents that call real tools. What makes it different: every pattern comes with working Python code, a real failure case study, and a "what can go wrong" section — not just theory.

• 
  Venn.aiMar 2026 · venn.ai · ▲336

  Delegate real work to AI agents with safety guardrails

• 
  I built a firewall for agents because prompt engineering isn't securityJan 2026 · github.com · ▲7

  Hi HN, I’m the creator of Cordum. I’ve been working in DevOps and infrastructure for years (currently in the fintech/security space), and as I started playing with AI agents, I noticed a scary pattern. Most "safety" mechanisms rely on system prompts ("Please don't do X") or flimsy Python logic inside the agent itself. If we treat agents as autonomous employees, giving them root access and hoping they listen to instructions felt insane to me. I wanted a way to enforce hard constraints that the LLM cannot override, no matter how "jailbroken" it gets. So I built Cordum. It’s an open-source…

• 
  OpenClaw-superpowers – Self-modifying skill library for OpenClaw agentsMar 2026 · github.com · ▲8

  I built a skill library for OpenClaw (always-on AI agent runtime, not session-based) where the agent can teach itself new behaviors during normal conversation. The idea: you tell your agent "every time I ask for a code review, always check for security issues first." It invokes a create-skill skill, writes a new SKILL.md, and that behavior is live immediately — no restart, no config change, no developer required. What I think is actually useful (the safety cluster): • loop-circuit-breaker: OpenClaw retries ALL errors identically. This halts on the 2nd identical failure before it burns your…

• 
  Whetstone – 20 Claude Code skills, each distilled from one real failureAug 2026 · whetstone.akbarsha.dev · ▲6

  24 agent skills, each distilled from one concrete engineering failure — short, self-contained rule sets an AI coding agent (or a human) can apply without the original context.

• 
  AI Coding Agent Guardrails enforced at runtimeApr 2026 · sigmashake.com · ▲5

  As a Security Engineer with over 10+ years in industry, I kept running into the same problem with coding agents: Instructions are not guarantees. I put guidance in `CLAUDE.md`, `AGENTS.md`, memory files, MCP descriptions, and tool documentation. I explicitly told the agent things like: - Use the code graph for architecture questions instead of grepping the repository. - Do not use deprecated APIs or Unsafe code. - Prefer specific tools for specific tasks. The agent would still ignore those instructions surprisingly often. It would grep the entire repo, use deprecated APIs, or choose a slower…

• 
  Agent StackMay 2026 · npmjs.com · ▲2

  5 tiny npm libs to stop AI agents misbehaving in prd

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 18d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 18d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 20d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 21d ago · stillwet.art

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 30d ago · world.pixverse.video

• 
  Beam.win▲378

  Run AI agents on one Mac and use its windows on another

  AI · 4d ago · beam.win

• TL
  The load-bearing vocabulary of Claude▲710

  Life & fun · Aug 2026 · louisabraham.github.io

• 
  Hey Noah▲656

  A proactive AI executive assistant for founders

  AI · Aug 2026 · heynoah.io

• 
  Clipto MCP▲655

  Hey HN, We recently built Clipto. It’s a tool that lets you search over terabytes of video, audio, and images on your computer, without relying on the cloud. Motivation: we probably all had this similar experience, we know a moment exists in a video or audio, but finding it takes hours scrubbing the timeline. You can send all the media to process in the cloud, but it’s slow, expensive and raises privacy concerns. So we decided to build our own on-device media search engine. How it works (high level): 1. We ingest video, audio, image; normalize formats via ffmpeg; run content analysis to…

  Work · Aug 2026 · clipto.com

• 
  Simple algorithm and color space to generate diverse skin tones▲627

  Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…

  Life & fun · Aug 2026 · toneyalexander.github.io

• 
  AdAnt AI▲620

  Claude for viral, high-converting social ads

  AI · Aug 2026 · adant.ai

• 
  Astute▲606

  Automate your B2B brand going viral, with new media creators

  AI · Aug 2026 · company-app.joinastute.com