# k8sgpt-ai/k8sgpt

Giving Kubernetes Superpowers to everyone

Repository: https://github.com/k8sgpt-ai/k8sgpt
Canonical: https://ross.abutalabs.com/products/k8sgpt
Homepage: http://k8sgpt.ai
Language: Go
License: Apache-2.0
License Family: permissive
Topics: devops, kubernetes, openai, sre, tooling, ai, llama
Last push: 2026-08-26T20:59:40+00:00

## Health v2 (maintenance only)
Score: 97/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 90
- inputs: {"age_days": 1261, "days_push": 7, "days_rel": 6, "gap_med": 6, "n_releases_24m": 48}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8120, forks 1045 (observed 2026-08-28T04:10:13.490710+00:00)

## What it is
k8sgpt is a CLI tool that scans Kubernetes clusters, diagnoses issues, and triages them in plain English using AI backends like OpenAI, Azure, Bedrock, Gemini, and local models. It codifies SRE expertise into analyzers that extract the most relevant cluster information and enrich it with LLM explanations.

## Use cases
- diagnose why my kubernetes pod is crashlooping
- triage kubernetes cluster issues with ai
- explain kubernetes error events in plain english
- scan a k8s cluster for problems before an incident
- use an llm to debug kubernetes workloads
- run sre-style analysis on my cluster from the terminal

## When to choose
- you operate Kubernetes clusters and want fast, AI-assisted diagnosis of errors
- you want SRE knowledge codified into automated analyzers
- you need support for multiple LLM backends including local models
- you prefer a CLI-first workflow for cluster troubleshooting

## When to avoid
- you need full observability metrics, tracing, or long-term monitoring rather than point-in-time diagnosis
- you cannot send cluster data to an LLM and don't want to run local models
- you are not using Kubernetes

## Facets
- artifact type: cli-tool
- maturity: active
- function: cli, monitoring, llm-inference, agent-framework, developer-tools
- domain: artificial-intelligence, large-language-models, monitoring, cloud-computing
- platform: cli, go, windows, self-hosted
- tags: kubernetes, sre, diagnostics, troubleshooting, ai-assistant, mcp, openai, local-llm, devops, containers, linux, macos, docker

## Member repositories
- k8sgpt-ai/k8sgpt (main) score 97

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:13.490710+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:30:37.949783+00:00, confidence not recorded.
  - readme: https://github.com/k8sgpt-ai/k8sgpt (fetched 2026-08-28T04:10:13.490710+00:00, sha def3221173f2)
  - homepage: http://k8sgpt.ai (fetched 2026-08-29T08:28:38.467205+00:00, sha 18501623dc6c)
- Data as of 2026-08-30T08:39:29.467469+00:00.