#7272nd of 80 in Agent platforms

kubectl-ai

Kubernetes CLI agent that turns plain-language requests into kubectl operations

Stars
7.6k
License
Apache-2.0
Last commit
Jul 2026
Last release
Mar 2026
Language
Go
Stars, last 29 weeks+242
21 Apr 2026: 7,360 stars28 Apr 2026: 7,370 stars5 May 2026: 7,377 stars12 May 2026: 7,392 stars19 May 2026: 7,403 stars26 May 2026: 7,416 stars2 Jun 2026: 7,424 stars9 Jun 2026: 7,436 stars16 Jun 2026: 7,442 stars23 Jun 2026: 7,452 stars30 Jun 2026: 7,457 stars7 Jul 2026: 7,463 stars14 Jul 2026: 7,473 stars21 Jul 2026: 7,480 stars28 Jul 2026: 7,492 stars4 Aug 2026: 7,502 stars11 Aug 2026: 7,510 stars18 Aug 2026: 7,516 stars25 Aug 2026: 7,528 stars1 Sept 2026: 7,533 stars8 Sept 2026: 7,542 stars15 Sept 2026: 7,544 stars22 Sept 2026: 7,548 stars29 Sept 2026: 7,555 stars6 Oct 2026: 7,561 stars13 Oct 2026: 7,577 stars20 Oct 2026: 7,584 stars27 Oct 2026: 7,592 stars3 Nov 2026: 7,597 stars10 Nov 2026: 7,602 stars

7,360 on 21 Apr 20267,602 on 10 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

kubectl-ai is a Go CLI and kubectl plugin that sends a prompt to an LLM, which proposes and runs kubectl and bash commands against your cluster. It supports Gemini (default), Vertex AI, OpenAI, Azure OpenAI, Grok, Bedrock, Ollama and llama.cpp. It can also act as an MCP server or client, and offers a terminal or web UI.

Who it is for: Kubernetes operators who want an LLM agent in the terminal

Strengths

  • Works with many providers, including local Ollama and llama.cpp models
  • Runs interactively, one-shot, or from stdin pipes, and as a `kubectl ai` plugin
  • Acts as MCP server and client; custom tools are defined in YAML
  • Opt-in session save and resume across runs

Weaknesses

  • Not an officially supported Google product
  • MCP streamable-http endpoint is unauthenticated unless OAuth 2.1 flags are set
  • Local models need --enable-tool-use-shim for tool calling
  • Runs kubectl and bash, so cluster changes depend on LLM output and permission prompts

What it needs

  • no GPU
  • Needs kubectl, LLM provider API key or local Ollama/llama.cpp
  • Models: gemini, vertexai, openai, azopenai, grok
  • port 8888

Quick answers

Is kubectl-ai open source?

Yes. Its code is on GitHub under the Apache-2.0 license.

Can you run kubectl-ai with Docker?

Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.

Does kubectl-ai need a GPU?

No, it runs without one.

Also in Agent platforms

See all 80
Also in Agent platforms
RankProjectScore
1AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder Live demo ↗ (opens in a new tab)188k stars+853 (+0.5%) in 30 dayscustom license95 out of 100
2daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps69.9k stars+3,683 (+5.6%) in 30 daysMIT95 out of 100
3LangflowVisual builder for AI agents and workflows, exposed as API or MCP server156.5k stars+1,251 (+0.8%) in 30 daysMIT94 out of 100
#4deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills85.2k stars+1,752 (+2.1%) in 30 daysMIT93 out of 100
#5DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs Live demo ↗ (opens in a new tab)161k stars+3,111 (+2.0%) in 30 dayscustom license92 out of 100