agents-cli vs LangGraph
CLI + agent-skills layer that turns your coding assistant into a Google Cloud agent-lifecycle expert: scaffold ADK projects, run and evaluate them, then deploy and publish to Gemini Enterprise. — versus — Build stateful, multi-actor LLM apps as graphs — durable execution, human-in-the-loop, streaming.
Both are ways to build production agentic apps, but from opposite ends: LangGraph is an open, embeddable graph runtime that runs anywhere, while agents-cli is Google's CLI+skills around ADK that scaffolds, evaluates, and deploys agents specifically on Google Cloud / Gemini Enterprise. Choose by ecosystem and portability needs.
| agents-cli | LangGraph | |
|---|---|---|
| Stars | 5.2k | 37k |
| Forks | 542 | 6.3k |
| Language | Python | Python |
| License | Apache-2.0 | MIT |
| Last activity | 7 days ago | 2 days ago |
| Topics | coding, evals, skills | agents, orchestration |
| Curated connections | 5 | 16 |
agents-cli — the curator's take
Reach for agents-cli when you're building and shipping agents ON Google Cloud / Gemini Enterprise and want one CLI for scaffold → eval → deploy, driven through a coding agent you already use. NOT the pick if you're not on Google Cloud — deploy targets and publish are GCP/Gemini-bound — or if you want a portable, vendor-neutral framework to embed in your own app; a framework like LangGraph or CrewAI fits that better.
LangGraph — the curator's take
You reach for LangGraph the moment a simple agent loop stops being enough — when you need state that survives a crash, a human approving a step mid-run, or a flow that can loop back on itself. Most teams arrive here from plain LangChain and don't leave. If all you want is a quick tool-calling agent, this is more machinery than you need — start lighter and come back when you hit the wall.