Policy enforcement for Claude Code, Cursor, and Codex
Show HN: Runtime authorization for Claude Code, Cursor, and Codex Hi HN, Fernando and I built Kastra. Kastra intercepts AI agent tool calls and evaluates them against deterministic policies before they execute. This is aimed at developers using coding agents like Claude Code, Codex, Cursor, and OpenClaw. We built Kastra after one of our Cursor agents almost executed DELETE FROM customers WHERE status='test' against a production database. We caught it before it ran, but it made us realize that nothing in our stack actually decided what the agent was allowed to do. What mattered for us wasn't…
In plain words
Kastra is a runtime authorization system for AI coding agents like Claude Code, Cursor, and Codex. It intercepts and evaluates tool calls against deterministic policies before execution, preventing agents from performing unintended actions like dangerous database operations. Designed for developers using AI agents in production environments, Kastra adds a policy layer that ensures agents can only perform explicitly allowed actions, addressing the gap where LLMs make probabilistic decisions without built-in safeguards.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Show HN: Runtime authorization for Claude Code, Cursor, and Codex Hi HN, Fernando and I built Kastra. Kastra intercepts AI agent tool calls and evaluates them against deterministic policies before they execute. This is aimed at developers using coding agents like Claude Code, Codex, Cursor, and OpenClaw. We built Kastra after one of our Cursor agents almost executed DELETE FROM customers WHERE status='test' against a production database. We caught it before it ran, but it made us realize that nothing in our stack actually decided what the agent was allowed to do. What mattered for us wasn't the mistake; it was realizing nothing in our setup would have stopped it if we weren't actively on top of it. LLMs are probabilistic, and prompts influence behavior, but they don't deterministically decide what an agent is allowed to do. Without a deterministic policy system, nothing could have decided what it was allowed to do. Kastra pushes an allow, hold, and deny decision before the action runs. You can build these policies in plain English from the web app. The interception engine evaluates the tools, targets, and parameters of every action. We also shipped many policy packs covering common high-risk scenarios, and every decision is recorded in an immutable audit trail. The desktop app, CLI, dashboard, and Recon scan are free to use for developers. If you often use Claude, Codex, Openclaw, and Cursor, Kastra can run a scan command on which risky actions your agents have already taken and automatically build rules to avoid them from happening again. Recon is a feature of Kastra that scans your local agent history. In order to run this scan, execute the commands below in your coding agent. brew install kastra-labs/tap/kastra-edge kastra-edge scan The scan reads your local agent session history, and it shows all the risky actions your agent has already taken before, the secrets written to tracked files, production databases touched, force pushes, curl-to-shell, and more. This runs on your machine, and secrets never leave. In our own use cases, we kept finding things we'd forgotten or didnt know agents had done. Each finding can be converted into a runtime policy, letting you delegate more work to AI without trusting the model itself. Kastra intercepts all workloads at runtime and makes sure these policy evaluations typically complete in under a millisecond. Instead of trusting the model, you trust the deterministic rules that govern its actions. One problem we are still working on to improve the stack is how to manage teams of agents with conflicting policies. We would love feedback from anyone building multi-agent systems. Fernando and I will be reviewing the comments. We are super curious what your first scan finds. Please post results below so we can see what the most common patterns are and adjust policy packs for our users based on your feedback. Documentation: https://kastra.ai/docs Download for MacOS Kastra Edge: https://kastra.ai/edge/download.html Check Kastra in action today: https://www.youtube.com/watch?v=6TUETu5lb3Q&feature=youtu.be
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 · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d 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 · 26d ago · cactuscompute.com
Launched alongside, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- EElevators▲1,680
Life & fun · Jul 2026 · john.fun
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
