Certus
Liability insurance for AI agents. One line of code
What it does
Your AI agent is one hallucination away from a lawsuit. Traditional insurers are filing exclusions for AI claims. Certus wraps your agent in a single line of code, generates cryptographic proof of every action it takes, scores risk in real-time. We’re building the verification and risk infrastructure that the AI agent economy needs. This is the foundation that makes AI agents accountable - and eventually, insurable. Safe agents pay less. Risky ones pay more. Like Tesla Insurance, but for AI.
Does a similar job
all alternatives →
- IBI 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…
- IBI built an AI extension to protect your wallet from sneaky clauses2025 · aayen.org · ▲5
I got tired of slogging through walls of legal text whenever I had to sign something important, so I built a Chrome extension that uses AI to: - Spot red flags and suspicious clauses – It automatically highlights risk areas in real-time as you read through an online contract. - Score the contract’s safety – Based on industry-standard risk parameters, it gives you an at-a-glance score so you can see how risky the document might be. - Simplify the jargon – It generates a quick summary of the key points, saving you from reading every paragraph in detail. No more signing on hunches or bets!…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
