Prismer-AI

K8s4claw

Name: K8s4claw
Author: Prismer-AI

Security community

SOURCE https://github.com/Prismer-AI/k8s4claw

Description

The Kubernetes operator where AI agents manage their own infrastructure. Self-healing via intent annotations, Ed25519-signed audit, graceful LLM fallback.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

k8s4claw

[![CI](https://github.com/Prismer-AI/k8s4claw/actions/workflows/ci.yml/badge.svg)](https://github.com/Prismer-AI/k8s4claw/actions/workflows/ci.yml) [![CodeQL](https://github.com/Prismer-AI/k8s4claw/actions/workflows/codeql.yml/badge.svg)](https://github.com/Prismer-AI/k8s4claw/actions/workflows/codeql.yml) [![Go Report Card](https://goreportcard.com/badge/github.com/Prismer-AI/k8s4claw)](https://goreportcard.com/report/github.com/Prismer-AI/k8s4claw) [![Release](https://img.shields.io/github/v/release/Prismer-AI/k8s4claw?sort=semver)](https://github.com/Prismer-AI/k8s4claw/releases) [![Go Reference](https://pkg.go.dev/badge/github.com/Prismer-AI/k8s4claw.svg)](https://pkg.go.dev/github.com/Prismer-AI/k8s4claw) [![License](https://img.shields.io/github/license/Prismer-AI/k8s4claw)](LICENSE) [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/Prismer-AI/k8s4claw?quickstart=1)

**A Kubernetes operator for AI agents that keeps the LLM out of the cluster's write path.** One CRD, any runtime (OpenClaw, NanoClaw, ZeroClaw, PicoClaw, IronClaw, HermesClaw, HermesRS, K8sOps), self-healing from day one.

The core idea

k8s4claw keeps the LLM out of the cluster's write path. **The agent's ServiceAccount cannot patch workload objects.** The LLM can only submit an `ops-intent` annotation on a Claw CR; a Go reconciler validates the intent's JSON shape against a 5-action allowlist (plus generation guard) and is the only component that mutates workloads. The reconciler also writes an Ed25519 audit receipt when the action runs through the auto-execute path — the signature is for the audit trail, not for authorization, and is non-blocking if signing fails.