Launching today
Kastra
Runtime authorization for Claude, Cursor, Codex and OpenClaw
191 followers
Runtime authorization for Claude, Cursor, Codex and OpenClaw
191 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.
I've been burned by an agent calling a tool it shouldn't have. A pre-execution control plane like this feels overdue, honestly.
Kastra
@grayson_carter3 Yes, this is a very common problem. We've heard similar stories from a lot of developers over the past few months. As agents become more autonomous, trusting them isn't enough; you also need deterministic guardrails around what they're allowed to do. That's the gap we set out to solve with Kastra.
The line I keep going back to is "approval now completes in about a second".
We run an approve-before-send step on the support side, and latency was never what broke it. Attention was. While the queue is short people actually read what they are approving. Once it gets long they stop reading and start clicking, and you have a human in the loop on paper but not in practice. Making approval fast is good, but it also makes it cheap, and cheap approvals get rubber-stamped.
I have never solved this properly, so genuinely asking: does the console show time-to-decision, not just allow/deny counts? A median of 0.4s across 200 approvals a day, and the same allow rate across 20, are two very different situations and only one of them is human-in-the-loop.
One smaller thing, and it may be out of scope for an authorization layer: the approver sees the action and the policy that matched. What usually decides whether an action should run is what the agent read three steps earlier. Do you carry any of that into the approval prompt?
Kastra
I've watched a few "AI firewall" products overpromise and underdeliver, so I'm cautiously optimistic rather than sold. What would actually convince me is seeing how this performs against a red-teamed agent trying to route around the rules, not just against a well-behaved one following the happy path.
Kastra
One control plane across Claude Cursor Codex and other tools feels practical for mixed environments. Does it support temporary project exceptions without weakening security? That flexibility could help development teams move faster.
Kastra
@jason_scott8 Yes, teams can create project-specific or time-limited policy exceptions while keeping organization-wide guardrails in place. That way, developers can unblock legitimate work without permanently weakening their security posture. The idea is to make exceptions explicit, auditable, and easy to revoke.
Our "Teams" plan also allows CTOs and Engineering leaders to push policies down to their employees for company-wide rules; these are enforced locally and also with their cloud and browser agents or plugged directly into the LLM SDKs for custom integrations.
Love the recon scan to know all the unexpected/dangerous things Claude Code has done in the past. Some things I already knew but it caught some others I didn't know about it. And with automatic policy generation I don't need to worry about it messing up again!
Kastra
@churds Exactly, Richard, this gives you a baseline of policies that adjust to your coding behavior first. Then, once you have this baseline, you can build new daily policies on top of them to continue reducing risks you learn along the way. Some Recon scans from our customers show many important high-risk actions they were not aware of; some thought they were protected with their existing frameworks, and the reality was different.
I like that this doesn't ask me to trust the agent's judgment at all, it just checks the action against a rule before anything happens. That's the right mental model. Most of the "AI safety" tooling I've evaluated this year still leans on the model behaving well, which never sat right with me.
Kastra
@thomas_jack3 Very accurate! We learned this by testing the product with some of the top enterprises pushing AI products into production. We realized autonomous AI products required a new infra layer and we built Kastra to solve the trust problem in a scalable way.
What I like here is the scope, one control plane across Claude Code, Cursor, Codex and OpenClaw. I've juggled separate configs for each tool before, and it's a mess nobody talks about enough.
Kastra