Back to browse
GitHub Repository

Deep research for your infra. Cynative runs frontier models across your code, cloud and runtime - reasoning through GitHub, GitLab, AWS, GCP, Azure and Kubernetes as one system - and comes back with verified answers.

146 starsGo

Cynative – Read-only CLI in Go that explains your live infrastructure

by szin·Jul 28, 2026·16 points·4 comments

AI Analysis

●●●BangerBig BrainWizardry

Sandboxed agent verifies findings across code and runtime where Prowler and Datadog only scan.

Strengths
  • Action gate architecture enforces read-only policies before any credential is attached to calls.
  • Generates and executes ephemeral code to fan out queries across multiple cloud providers simultaneously.
  • Automatically refreshes allowed action sets from provider APIs every 24 hours to stay current.
Weaknesses
  • Requires frontier model API keys which adds cost and latency to every audit query.
  • Complex setup for self-hosted Kubernetes clusters compared to managed cloud environments.
Category
Target Audience

DevSecOps engineers and platform teams managing multi-cloud infrastructure

Similar To

Prowler · Datadog Cloud Security · Wiz

Post Description

Hey, we built an open-source CLI in Go purposed to help you answer security questions across your cloud, code and runtime. It connects to your GitHub, GitLab, AWS, GCP, Azure & K8s using the credentials that are already in your shell, while limiting itself to read-only.

The core innovation here is the trust boundary - our agent has a built-in code execution sandbox with no host or network access; it is exposed to an internal tool which we call an “action gate” that performs read-only HTTP requests to your own infrastructure. Since the cloud providers constantly expand actions and services, the read-only allowed set comes from the providers themselves, refreshed every 24 hours (and is configurable).

Some additional neat features: verifiers that recheck every finding, fail-closed audit log, host-pinning to your own infra, STS rescoping to SecurityAudit in AWS AssumeRole, secret redaction so the LLM never sees them, and much more.

Even though the frontier models are becoming quite capable at answering broad security questions like “review my code” or “audit my cloud security posture”, we’d recommend starting with something more specific, like “what in my cloud is publicly exposed and shouldn’t be?” or “can my CI escalate to cloud admin?”.

Repo and documentation available here: https://github.com/cynative/cynative

Would love to hear any feedback / feature requests.

Similar Projects

Security●●Solid

Audit your Linux VPS security in one command

Self-deleting script runs 25 checks but sends raw data to a central backend.

Ship ItSolve My Problem
juanisidoro
202mo ago