# kagent-dev/kagent

Cloud Native Agentic AI | Discord: https://bit.ly/kagentdiscord

Repository: https://github.com/kagent-dev/kagent
Canonical: https://ross.abutalabs.com/products/kagent
Homepage: https://kagent.dev
Language: Go
License: Apache-2.0
License Family: permissive
Topics: agents, ai, cncf, devops, mcp
Last push: 2026-08-26T22:10:35+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 42
- inputs: {"age_days": 589, "days_push": 7, "days_rel": 15, "gap_med": 1, "n_releases_24m": 162}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3595, forks 728 (observed 2026-08-28T04:08:11.271768+00:00)

## What it is
kagent is a Kubernetes-native framework for building, deploying, and managing AI agents as first-class Kubernetes resources via CRDs. It supports multiple LLM providers, MCP tool servers, agent-to-agent (A2A) communication, and brings GitOps, RBAC, and observability to agentic AI workloads.

## Use cases
- run AI agents on kubernetes
- define agents as kubernetes CRDs with gitops
- add MCP tools to AI agents
- troubleshoot kubernetes clusters with AI agents
- automate kubernetes operations with LLM agents
- build multi-agent workflows with A2A communication
- deploy agents with RBAC and observability
- connect agents to OpenAI Anthropic Gemini models

## When to choose
- you already run workloads on Kubernetes and want agents managed with the same CRDs, RBAC, and GitOps tooling
- you need multi-LLM and multi-framework support (OpenAI, Anthropic, Gemini, LangGraph, CrewAI, Google ADK) without vendor lock-in
- you want MCP tool integration and agent-to-agent communication out of the box
- you need production-grade observability (OpenTelemetry, Prometheus) and zero-trust security for agent traffic

## When to avoid
- you have no Kubernetes cluster or want a simple local-only agent runtime
- you need a lightweight standalone agent script without cluster infrastructure overhead
- your use case is a simple chatbot UI without Kubernetes operations
- you are not prepared to manage Helm charts, CRDs, and cluster add-ons

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, mcp, llm-inference, chatbot, monitoring, workflow-automation
- domain: large-language-models, cloud-computing, self-hosted
- platform: go, python, self-hosted, cli
- tags: kubernetes-native, crds, gitops, a2a, declarative-agents, cncf-sandbox, observability, multi-llm, ai-agents, devops, kubernetes, docker

## Member repositories
- kagent-dev/kagent (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:11.271768+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 2026-08-29T18:33:48.452932+00:00, confidence not recorded.
  - readme: https://github.com/kagent-dev/kagent (fetched 2026-08-28T04:08:11.271768+00:00, sha 8c7e893cb2fd)
  - homepage: https://kagent.dev (fetched 2026-08-29T09:27:12.242407+00:00, sha fd396a4c2d35)
  - site_page: https://kagent.dev/docs/kagent/getting-started/quickstart (fetched 2026-08-29T09:27:12.245351+00:00, sha b0058ff0e0c6)
  - site_page: https://kagent.dev/docs/kagent (fetched 2026-08-29T09:27:12.247201+00:00, sha 5bf43faafcc4)
  - site_page: https://kagent.dev/docs/kagent/introduction/installation (fetched 2026-08-29T09:27:12.249020+00:00, sha 8e60d6e199d1)
  - site_page: https://kagent.dev/docs/kagent/getting-started/first-agent (fetched 2026-08-29T09:27:12.250889+00:00, sha efc7c153f8a1)
  - site_page: https://kagent.dev/docs/kagent/getting-started/first-mcp-tool (fetched 2026-08-29T09:27:12.252954+00:00, sha 0e654805fa1c)
  - site_page: https://kagent.dev/docs/kagent/introduction/what-is-kagent (fetched 2026-08-29T09:27:12.255031+00:00, sha eaf736373451)
  - site_page: https://kagent.dev/docs/kagent/concepts/architecture (fetched 2026-08-29T09:27:12.256965+00:00, sha 30b56eb351e9)
  - site_page: https://kagent.dev/docs/kagent/concepts (fetched 2026-08-29T09:27:12.258641+00:00, sha 9c38355204ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.