Back to directory

KAOS

A Kubernetes-native framework for deploying and orchestrating AI agents as cluster resources, with hierarchical multi-agent delegation and an OpenAI-compatible chat endpoint on every agent.

KAOS

KAOS lets a developer describe an AI agent and a network of agents as Kubernetes custom resources, deployed and managed with a dedicated CLI or through Helm and kubectl. Every agent exposes an OpenAI-compatible chat completions endpoint, tools are wired in through the Model Context Protocol, and a coordinator agent can delegate parts of a task to specialist agents declared in the same resource, forming a hierarchical multi-agent system.

A visual dashboard, opened with the CLI, lets a developer monitor running agents, test chat interactions, and debug an agent's memory and tool calls; it can also be launched with monitoring enabled for further observability. The project's Kubernetes operator installs through a published Helm repository, and sample multi-agent configurations are provided for reference.

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.

  • 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.

  • 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.