---
title: "graph-agents-cli"
description: "Scaffold, develop, evaluate, and deploy LangGraph agents on self-hosted Kubernetes. Bundles skills for the agent development lifecycle."
canonical: https://agentpluginsdirectory.com/plugins/graph-agents-cli
last-updated: 2026-09-25
---

# graph-agents-cli
Scaffold, develop, evaluate, and deploy LangGraph agents on self-hosted Kubernetes. Bundles skills for the agent development lifecycle.
- Slug: graph-agents-cli
- Publisher: graph-agents-cli contributors
- Repository: https://github.com/ss7172/graph-agents-cli
- Manifest: plugin.json
- Version: 0.2.0
- License: Apache-2.0
- Category (editorial): other
- Skills: 6 (graph-agents-cli-deploy, graph-agents-cli-eval, graph-agents-cli-langgraph-code, graph-agents-cli-observability, graph-agents-cli-scaffold, graph-agents-cli-workflow)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-09-23
- Repository last pushed: 2026-09-25
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/graph-agents-cli
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What graph-agents-cli does, in the publisher's words

CLI and skills for building, evaluating, and deploying LangGraph agents on self-hosted Kubernetes.

graph-agents-cli scaffolds a LangGraph project with a chat API, an A2A endpoint, an eval harness, a Helm chart, and GitHub Actions workflows; runs and evaluates the agent locally; and deploys it to any Kubernetes cluster with Helm, either directly or through Argo CD. It ships six skills that teach a coding agent (Claude Code, Antigravity, Codex, Gemini CLI, Cursor) the same lifecycle.

It is a fork of google-agents-cli with the Google Cloud specific parts removed; see NOTICE. Status: first milestone under construction. See this README for the supported commands and behavior, and CONTRIBUTING.md for development and verification guidance.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/ss7172/graph-agents-cli/HEAD/README.md

## Skills

- graph-agents-cli-deploy: This skill should be used when the user wants to "deploy an agent", "deploy to Kubernetes", "deploy to our cluster", "set up CI/CD", "set up Argo CD", "configure secrets", "rotate a key", "promote to production", "check cluster prerequisites", "deploy to kind/k3s/minikube", "deploy air-gapped", or…
- graph-agents-cli-eval: This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "write an eval dataset", "add an eval case", "analyze eval failures", "compare eval results", "set a quality threshold", "why did eval exit 1", or "upload evals to LangSmith". Covers the enforceable eval gate…
- graph-agents-cli-langgraph-code: This skill should be used when the user wants to "write agent code", "build an agent with LangGraph", "add a tool", "add a node to the graph", "use a checkpointer", "stream events", "add human-in-the-loop", "add a subgraph", "switch the model provider", "implement the auth policy", "call the produc…
- graph-agents-cli-observability: This skill should be used when the user wants to "set up tracing", "enable LangSmith", "send traces to our collector", "monitor my agent", "debug production traffic", "see what the agent sent to the model", "log prompts", or needs guidance on observability for a graph-agents-cli project. Covers the…
- graph-agents-cli-scaffold: This skill should be used when the user wants to "create an agent project", "start a new LangGraph project", "build me a new agent", "scaffold a project", "add Kubernetes deployment", "add CI/CD to my project", "add Argo CD", "enhance my project", or "upgrade my project". Part of the graph-agents-c…
- graph-agents-cli-workflow: This skill should be used when the user wants to "develop an agent", "build an agent with LangGraph", "build a LangGraph agent", "run the agent locally", "debug agent code", "test an agent", "evaluate an agent", "deploy an agent to Kubernetes", "monitor an agent", or needs the graph-agents-cli deve…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.