Launching today
Kastra
Runtime authorization for Claude, Cursor, Codex and OpenClaw
436 followers
Runtime authorization for Claude, Cursor, Codex and OpenClaw
436 followers
Kastra is the runtime authorization layer for AI agents. It decides what agents can and cannot do before actions execute, enforcing policies with sub-1 ms latency across tools, prompts, inputs, and outputs. Use one control plane to govern agents and policies across Claude Code, Cursor, Codex, OpenClaw, the Anthropic SDK, the OpenAI SDK, and more. Prevent unauthorized tool use, prompt injection, and exposure of sensitive data before they become incidents. Trust the rules, not the agents.
The output-side check is the half most policy layers skip — gating on the agent's output before it executes, not just the input. Two things I'd wire-test first in a coding-agent loop: is the sub-1ms decision in-process/local, or a network hop to your control plane (which changes the latency math mid tool-call)? And when a policy can't reach a verdict in time, do you fail-closed by default, or is that configurable per-policy?
Carlos — "authorization doesn't carry over because the parent action was allowed" is the detail that got me. WinBidIQ's agent reads all kinds of docs — a public RFP one minute, a client's confidential pricing sheet the next. Does Kastra gate by action type only, or can policy also key off how sensitive the actual content is?
The "zero implicit trust" framing is really nice. Most agent safety thinking stops at the model level. Most actual work is on how to set actual programmatic hard walls
well done team:)
Kastra
I use Kastra everyday to discover the risks while coding and it’s very useful.
Highly recommend 👍🏻
Kastra
@carlos_campos93 This is great, thank you. We're happy we can bring value to you!
I have been testing kastra with my team and even though I’m not very technical it’s very simple to use and it has helped us a lot while building our product.
Kastra
@paula_jimenez4 Kastra is great for new builders learning how to code; it teaches them the risks and helps them understand the agentic coding workloads better by being able to evaluate all the actions, risks, and decisions at runtime.
Lancepilot
Kastra
Kastra
Thank you@odeth_negapatan1, that's exactly the gap we set out to close!
EverTutor AI
This is the kind of infrastructure that won't get the loudest headlines, but could become a core part of every serious AI stack. As agents gain more autonomy, authorization becomes just as important as intelligence. Congrats to the entire team and wishing you an amazing launch
Kastra