kubectl-ai - AI Developer Tools Tool

Overview

kubectl-ai is an open-source, AI-powered kubectl extension that translates natural-language intent into precise Kubernetes operations, helping operators and developers interact with clusters from the terminal or a small web UI. It supports interactive chat-style sessions and single-shot query mode, can read stdin, and returns both kubectl output and human-friendly explanations — for example: kubectl-ai --quiet "scale the nginx deployment to 5 replicas" will run the necessary kubectl commands and explain what changed. ([github.com](https://github.com/GoogleCloudPlatform/kubectl-ai?utm_source=openai)) The tool is provider-agnostic and runs with cloud LLMs (Gemini, Vertex AI, OpenAI, Azure OpenAI, AWS Bedrock/grok/Claude) as well as local model backends (ollama, llama.cpp). Advanced capabilities include session persistence (new/list/resume/delete sessions), multiline input support, a terminal-first UI plus an optional web UI, and MCP server/client modes to expose or consume external tools. kubectl-ai also ships k8s-ai-bench (a benchmarking suite) and a Docker image for isolated usage. The project publishes regular releases and changelogs on GitHub. ([github.com](https://github.com/GoogleCloudPlatform/kubectl-ai?utm_source=openai))

GitHub Statistics

• Stars: 7,164
• Forks: 655
• Contributors: 51
• License: Apache-2.0
• Primary Language: Go
• Last Updated: 2025-12-18T20:55:53Z
• Latest Release: v0.0.28

The repository is active and community-driven: the GitHub project shows ~7.2k stars and ~655 forks, an Apache-2.0 license, and an active releases stream (latest tag v0.0.28). Issue and PR activity indicates ongoing maintenance and community contributions. The project includes multiple contributors and frequent small releases and fixes, with benchmarks and docs receiving recent updates. ([github.com](https://github.com/GoogleCloudPlatform/kubectl-ai/releases))

Installation

Install via docker:

Quick (Linux/macOS): curl -sSL https://raw.githubusercontent.com/GoogleCloudPlatform/kubectl-ai/main/install.sh | bash

Manual (download + install): tar -zxvf kubectl-ai_Darwin_arm64.tar.gz && chmod a+x kubectl-ai && sudo mv kubectl-ai /usr/local/bin/

Install via krew (as kubectl plugin): kubectl krew install ai

Docker (build image): git clone https://github.com/GoogleCloudPlatform/kubectl-ai.git && cd kubectl-ai && docker build -t kubectl-ai:latest -f images/kubectl-ai/Dockerfile .

Docker (run sample with GKE): docker run --rm -it -p 8080:8080 -v ~/.kube:/root/.kube -v ~/.config/gcloud:/root/.config/gcloud -e GOOGLE_CLOUD_PROJECT=my-gcp-project kubectl-ai:latest --llm-provider vertexai --ui-listen-address 0.0.0.0:8080 --ui-type web

Key Features

• Natural-language queries that produce kubectl commands and human-readable explanations.
• Multi-provider LLM support: Gemini, Vertex AI, OpenAI, Azure, Bedrock, grok, ollama, llama.cpp.
• Session persistence: opt-in save, list, resume, and delete conversational sessions.
• MCP server/client modes to expose or consume external tools across LLM ecosystems.
• Terminal-first UI plus optional web UI and JSON/JSONL outputs for automation and benchmarks.

Community

Active community engagement with issue and PR activity, documentation updates, and benchmark work; the GitHub repo reports ~95 open issues and frequent releases. Contributions and discussions are ongoing across issues, PRs, and release notes — good for users seeking community support and contributors wanting to help. ([github.com](https://github.com/GoogleCloudPlatform/kubectl-ai/releases))

Key Information

• Category: Developer Tools
• Type: AI Developer Tools Tool