kagent

A Kubernetes-native framework for building, deploying and managing AI agents as Kubernetes custom resources.

kagent is a Kubernetes-native framework for building AI agents. Agents are defined as a system prompt, a set of tools and agents, and an LLM configuration, represented as a Kubernetes custom resource called an Agent.

It supports multiple LLM providers, including OpenAI, Azure OpenAI, Anthropic, Google Vertex AI and Ollama, configured through a ModelConfig resource, and it ships its own MCP server offering tools for Kubernetes, Istio, Helm, Argo, Prometheus, Grafana and Cilium, exposed as ToolServer custom resources that multiple agents can share.

It has four components: a controller that reconciles the custom resources, a web UI, an engine that runs agents, and a CLI, and it supports OpenTelemetry tracing for observability.

More in Agent frameworks

See all 902

Recurse
recurse.run
A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.
- Agent frameworks
ProofForge
shulgin.is-a.dev
An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.
- Agent frameworks
local-coder
github.com
Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.
- Coding agents
- Agent frameworks

More in Agent frameworks

Recurse

ProofForge

local-coder

Cookies