{"id":30847495,"url":"https://github.com/mckinsey/agents-at-scale-ark","last_synced_at":"2026-05-08T21:02:35.685Z","repository":{"id":312098832,"uuid":"1046380920","full_name":"mckinsey/agents-at-scale-ark","owner":"mckinsey","description":"Provider-agnostic operations for agentic resources. ARK codifies patterns and practices developed across dozens of agentic application projects.","archived":false,"fork":false,"pushed_at":"2026-05-08T18:34:30.000Z","size":115411,"stargazers_count":384,"open_issues_count":316,"forks_count":85,"subscribers_count":4,"default_branch":"main","last_synced_at":"2026-05-08T18:38:41.830Z","etag":null,"topics":["agentic-ai","ai","cloud","devops","kubernetes","productid-20863"],"latest_commit_sha":null,"homepage":"https://mckinsey.github.io/agents-at-scale-ark/","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mckinsey.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-08-28T15:48:47.000Z","updated_at":"2026-05-08T18:27:58.000Z","dependencies_parsed_at":"2025-10-26T17:38:02.652Z","dependency_job_id":null,"html_url":"https://github.com/mckinsey/agents-at-scale-ark","commit_stats":null,"previous_names":["mckinsey/agents-at-scale-ark"],"tags_count":37,"template":false,"template_full_name":null,"purl":"pkg:github/mckinsey/agents-at-scale-ark","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mckinsey%2Fagents-at-scale-ark","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mckinsey%2Fagents-at-scale-ark/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mckinsey%2Fagents-at-scale-ark/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mckinsey%2Fagents-at-scale-ark/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mckinsey","download_url":"https://codeload.github.com/mckinsey/agents-at-scale-ark/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mckinsey%2Fagents-at-scale-ark/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32797265,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-08T08:22:46.396Z","status":"ssl_error","status_checked_at":"2026-05-08T08:22:45.650Z","response_time":54,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentic-ai","ai","cloud","devops","kubernetes","productid-20863"],"created_at":"2025-09-07T02:13:17.689Z","updated_at":"2026-05-08T21:02:35.680Z","avatar_url":"https://github.com/mckinsey.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003ch1 align=\"center\"\u003e\u003ccode\u003e⚒️ ark\u003c/code\u003e\u003c/h1\u003e\n  \u003ch4 align=\"center\"\u003eAgentic Runtime for Kubernetes\u003c/h4\u003e\n  \u003cp align=\"center\"\u003e\n    \u003cstrong\u003eA declarative, Kubernetes-native framework for building portable, scalable, and provider-agnostic agentic applications.\u003c/strong\u003e\n  \u003c/p\u003e\n\n  \u003chr\u003e\n\n  \u003cp align=\"center\"\u003e\n    \u003ca href=\"#features\"\u003eFeatures\u003c/a\u003e •\n    \u003ca href=\"#quickstart\"\u003eQuickstart\u003c/a\u003e •\n    \u003ca href=\"https://mckinsey.github.io/agents-at-scale-ark/\"\u003eDocumentation\u003c/a\u003e\n  \u003c/p\u003e\n  \u003cp align=\"center\"\u003e\n    \u003ca href=\"https://github.com/mckinsey/agents-at-scale-ark/actions/workflows/cicd.yaml\"\u003e\u003cimg src=\"https://github.com/mckinsey/agents-at-scale-ark/actions/workflows/cicd.yaml/badge.svg\" alt=\"CI/CD\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://github.com/mckinsey/agents-at-scale-ark/actions/workflows/deploy.yml\"\u003e\u003cimg src=\"https://github.com/mckinsey/agents-at-scale-ark/actions/workflows/deploy.yml/badge.svg\" alt=\"Deploy\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://github.com/mckinsey/agents-at-scale-ark/actions/workflows/deploy_gcp.yml\"\u003e\u003cimg src=\"https://github.com/mckinsey/agents-at-scale-ark/actions/workflows/deploy_gcp.yml/badge.svg\" alt=\"Deploy GCP\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://codecov.io/gh/mckinsey/agents-at-scale-ark\"\u003e\u003cimg src=\"https://codecov.io/gh/mckinsey/agents-at-scale-ark/branch/main/graph/badge.svg\" alt=\"Coverage\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://github.com/mckinsey/agents-at-scale-ark/actions/workflows/sonar_scan.yaml\"\u003e\u003cimg src=\"https://github.com/mckinsey/agents-at-scale-ark/actions/workflows/sonar_scan.yaml/badge.svg\" alt=\"SonarQube Scan\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://www.npmjs.com/package/@agents-at-scale/ark\"\u003e\u003cimg src=\"https://img.shields.io/npm/v/@agents-at-scale/ark.svg\" alt=\"npm version\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://pypi.org/project/ark-sdk/\"\u003e\u003cimg src=\"https://img.shields.io/pypi/v/ark-sdk.svg\" alt=\"PyPI version\"\u003e\u003c/a\u003e\n  \u003c/p\u003e\n\u003c/div\u003e\n\n## What is Ark?\n\nArk is a declarative toolkit for building and hosting distributed AI agents. By defining what agents should do rather than how they do it, Ark eliminates vendor lock-in and ensures your applications stay adaptable as AI evolves.\n\nBuilt on Kubernetes, Ark lets you deploy a dev-friendly cluster in minutes or scale agentic workloads across existing infrastructure. Leverage proven patterns for security, monitoring, and RBAC—avoiding bespoke overhead while maintaining a portable, production-ready foundation for your AI projects.\n\n## Why Ark?\n\nArk is designed for rapid, democratic development of agentic systems. The entire stack is built on open-source Kubernetes technology designed for running distributed systems. It can run comfortably on a single developer's machine or be deployed into a Kubernetes cluster across multi-cloud and on-prem environments. Developers and operations teams have full visibility into the entire stack, from the highest to the lowest levels.\n\nBecause each workload is a declarative specification of agent behavior rather than proprietary code, teams can re-platform individual use cases onto specialized or proprietary stacks when needed, typically with minimal migration overhead.\n\n## Features\n\n- **Declarative Agents** — Define agents as Kubernetes custom resources with prompts, tools, and model references\n- **Provider Agnostic** — Swap between OpenAI, Anthropic, Google, Azure, or local Ollama without code changes\n- **Multi-Agent Teams** — Orchestrate agents with sequential, graph, selector, or round-robin strategies\n- **Tool Integration** — Connect agents to HTTP APIs, MCP servers, or other agents as tools\n- **Persistent Memory** — Maintain conversation context across sessions with pluggable memory backends\n- **A2A Protocol** — Interoperate with external agent systems via Agent-to-Agent protocol\n- **CLI \u0026 SDKs** — Manage agents from the command line or integrate via Python and TypeScript SDKs\n\n## Quickstart\n\nYou will need a Kubernetes cluster to install Ark into. You can use [Minikube](https://minikube.sigs.k8s.io/docs/start), [Kind](https://kind.sigs.k8s.io/docs/user/quick-start/), [Docker Desktop](https://docs.docker.com/desktop/kubernetes/) or similar to run a local cluster.\n\nEnsure you have [Node.js](https://nodejs.org/en/download) and [Helm](https://helm.sh/docs/intro/install/) installed. Then run the following commands to install Ark:\n\n```bash\n# Install the 'ark' CLI:\nnpm install -g @agents-at-scale/ark\n\n# Install Ark:\nark install\n\n# Optionally configure a 'default' model to use for agents:\nark models create default\n\n# Run the dashboard:\nark dashboard\n```\n\nIn most cases the default installation options will be sufficient. This will install the Ark dependencies, the controller, the APIs and the dashboard. You can optionally setup a `default` model that will be the default used by agents. The `install` command will warn if any required dependencies are missing.\n\nUser guides, developer guides, operations guides and API reference documentation is all available at:\n\nhttps://mckinsey.github.io/agents-at-scale-ark/\n\nTo troubleshoot an installation, run `ark status`.\n\n## Credits\n\nThe initial design and implementation of Ark was led by [Roman Galeev](https://github.com/Roman-Galeev), [Dave Kerr](https://github.com/dwmkerr), and [Chris Madden](https://github.com/cm94242).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmckinsey%2Fagents-at-scale-ark","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmckinsey%2Fagents-at-scale-ark","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmckinsey%2Fagents-at-scale-ark/lists"}