Skip to content
Agents tracked: 501 Releases (7d): 777 Agent status: no reported issuesSince last limit reset: Claude 10d · Codex 8d For AI agents: Markdown Updated Nov 21, 2026

K8sGPT

Scans Kubernetes clusters with built-in analysers, diagnoses problems and explains them in plain English using a choice of model backends; runs as a CLI, server, MCP server or in-cluster operator.

AI SRE and DevOps agents Open-source Kubernetes diagnosis agentOpen source · Apache-2.0Free to start

Use it in: CLI MCP server Self-hosted Works with: MCP Local models Own API key

Price
Free (OSS)
free and open source
Popularity
#3 in DevOps & SRE
Gid Score 17 / 100 · #236 of 255 ranked AI agents
Trend
—
about +3 GitHub stars a day
Development
Updated recently
latest 0.4.41, 31d ago
Community
8,344 GitHub stars
public signals

Usage data: latest readings Nov 20 to Nov 21, 2026, last checked Nov 21, 06:31 UTC. Date of each number

What K8sGPT does

K8sGPT is an open-source Kubernetes diagnosis agent from K8sGPT, first released in 2023. You use it through a command-line tool, MCP server and self-hosted on macOS, Windows and Linux. Its documentation covers your own API key and local models. It can run models from OpenAI, Azure, Amazon Bedrock and Google. It is free and open source (Apache-2.0); you pay only for the models it calls.

Key facts

MakerK8sGPT (CNCF Sandbox)
TypeOpen-source Kubernetes diagnosis agent
First released2023
LicenseApache-2.0
InterfacesCLI, MCP server, Self-hosted
PlatformsmacOS, Windows, Linux
Main languageGo
Open issues and PRs66

Pricing

Free and open source (Apache-2.0); bring your own model backend.

Source: official pricing page, checked Oct 6, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?Yes (Apache-2.0)
  • Runs onmacOS, Windows, Linux
  • Where you use itCLI, MCP server, Self-hosted
  • Model providersopenai, azure, amazon, google, local
  • Feature comparisonAll agents
  • Closest alternativeOpenSRE · all alternatives

What's new in K8sGPT: October 2026

Full monthly summary

October brought improvements to analyzer coverage and reliability, with better handling of edge cases across Kubernetes resource types and AI backend integrations.

  • Added ResourceClaim analyzer to detect missing DeviceClasses.
  • Support for Claude 4.5 and 5.x models on Amazon Bedrock.
  • Custom headers can now be sourced from the config file.
  • Auto-pull missing ollama models on demand.

2 releases this month · summarised from the official release notes · all months

AgentGid articles about K8sGPT

All guides

Get started with K8sGPT

Setup instructions are in the official documentation.

Compare K8sGPT with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
177
OpenSRETracer
28 79 up 61.2% up 128.6% 13.7K+127/day 0.1.2026.11.21today Free (OSS)
186
HolmesGPTRobusta (CNCF Sandbox)
27 4,854 down 0.1% up 54.2% 3,949+9/day 0.46.017d ago Free (OSS)
—
— — — — — — Usage-based
—
ClericCleric
— — — — — — Free + $700/mo
—
— — — — — — $25/mo
—
Resolve AIResolve AI
— — — — — — Usage-based

Head to head: K8sGPT vs OpenSRE · K8sGPT vs HolmesGPT · K8sGPT vs Bits AI SRE · K8sGPT vs Cleric · K8sGPT vs Resolve AI · K8sGPT vs Traversal

Ratings from people who use K8sGPT

No ratings yet. Used K8sGPT? Rate it and say what it is good and bad at.

What changed: recent K8sGPT releases

5 stable releases in the last 90 days · Monthly summary · Full changelog

0.4.41
  • add Claude 4.5 and 5.x models for Amazon Bedrock (a49636c)
  • enable to source customHeaders from the config file (37b87f1)
  • prompt to auto-pull missing ollama models (e977dc5)
  • accept an empty storageClassName in StatefulSet claim templates (642c3a4)
  • do not report an unsupported KEDA scaleTargetRef as missing (7fd1b40)
  • harden completion calls against empty responses and hangs (dca17b9)
0.4.40
  • add ResourceClaim analyzer for missing DeviceClasses (f2dd92e)
  • close the custom analyzer gRPC connection after each analysis (d6d75f7)
  • correct API doc lookups for the webhook analyzers (ce78560)
  • handle empty AI responses and respect configured language (9456068)
  • honor StatefulSet start ordinals (dd16466)
  • honour K8SGPT_BACKEND on every serve start (6959a93)
Earlier releases
0.4.39
  • add --resource flag to analyze a single resource (6863057)
  • add ValidatingAdmissionPolicy analyzer (c520d4a)
  • anonymise resource names in event-derived failures (1813838)
  • deps: update module google.golang.org/grpc to v1.83.1 [security] (e69dbc7)
  • deps: update module google.golang.org/grpc to v1.83.2 [security] (9c515b0)
  • do not also report an unsupported scaleTargetRef as missing (48737a8)
0.4.38
  • correct --with-stat flag description (ebd79ac)
  • validate namespace exists before running core analyzers (c7e91c0)
  • deps: update docker/setup-buildx-action digest to 37fe631 (92c0091)
  • deps: update softprops/action-gh-release digest to efb3536 (7e4e955)
0.4.37
  • add Amazon Bedrock Mantle (OpenAI-compatible) AI provider (bdbc3c7)
  • add LiteLLM backend (47db90f)
  • clamp max-concurrency in custom analysis to avoid deadlock and panic (6859e9c)
  • deps: update k8s.io/utils digest to cf1189d (8bda53b)
  • deps: update module google.golang.org/grpc to v1.82.1 [security] (1c8a56c)
  • do not panic on an Ingress path with a resource backend (b4a86de)
0.4.36
  • correct Vertex AI legacy model ids by removing stray asterisk (60a9794), closes
  • deps: update k8s.io/utils digest to be93311 (de01885)
  • deps: update module golang.org/x/net to v0.55.0 [security] (2e57a6f)
  • guard interplex cache Store and Load against nil grpc conn (238a97a)
  • send temperature or top_p exclusively for Anthropic models (2cda9d8)
  • deps: update docker/login-action action to v4 (60268ca)

K8sGPT prices over time

Token prices of OpenAI modelsnewest OpenAI model in each family, output price per 1M tokens
OpenAI FlagshipOpenAI Mini

K8sGPT popularity and usage data

The GitHub repository has 8,344 stars, 88 of them added in the last 30 days. The latest stable release is 0.4.41, published Oct 21, 2026.

GitHub starsrunning total 8,344
Website rankTranco list; a lower rank means more traffic #1,501,029

Download the raw daily series: k8sgpt.csv

Gid Score breakdown

Adoption0
Community38
Attention—
Momentum50

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
GitHub starsNov 21, 2026Nov 21, 06:26 UTC
Website rank (Tranco)Nov 20, 2026Nov 21, 06:31 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

K8sGPT FAQ

How much does K8sGPT cost?

Free and open source (Apache-2.0); bring your own model backend.

Is K8sGPT open source?

Yes. K8sGPT is open source, released under the Apache-2.0 license.

How popular is K8sGPT?

The GitHub repository has 8,344 stars, 88 of them added in the last 30 days. The latest stable release is 0.4.41, published Oct 21, 2026.

What is the latest version of K8sGPT?

The latest stable release we track is 0.4.41, published on Oct 21, 2026.

What are the alternatives to K8sGPT?

The closest alternatives in the same category by Gid Score are OpenSRE, HolmesGPT, Bits AI SRE, Cleric.

For the makers of K8sGPT badges, corrections

Add a live badge to your README or site:

AgentGid: #3 in DevOps & SRE Gid Score: 17/100

[![AgentGid: #3 in DevOps & SRE](https://agentgid.com/badges/k8sgpt-rank.svg)](https://agentgid.com/agents/k8sgpt/)
[![Gid Score: 17/100](https://agentgid.com/badges/k8sgpt-score.svg)](https://agentgid.com/agents/k8sgpt/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

GitHub: k8sgpt-ai/k8sgpt. Site rank: k8sgpt.ai on the Tranco list. See data sources for how each one is collected.

Product facts and pricing were checked against: github.com, cncf.io.