Skip to content
repository radar
Agents & Orchestration

☁️agents-cli

ACTIVE BREAKOUT

google/agents-cli · homepage ↗

The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.

⭐ Popular: 6k stars, gaining about 153 a week

View on GitHub ↗

repo profile

vintage 2026 launched this year
delivery product
language Python
license Apache-2.0

momentum

total stars 6k
stars added last week +153
binary downloads 20 total · GitHub releases
commits / week 1 cooling · -60% vs prior mo
issues closed 72% ~7d to close, median
contributors 5 (+1 in 15d)
release cadence weekly
last activity 11d ago

durability

backing company-owned Google
openness permissive
bus factor 1 solo
top-author share 60% 6 mo

bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.

since we covered it

monthly average + 1k/mo (+29%/mo) · + 2k total since PR#37

why it's a big deal

  • Gives coding assistants like Claude Code, Codex, and Antigravity CLI the skills to build, evaluate, and deploy agents on Google Cloud, targeting developers already working through an AI coding agent.
  • Covers the full lifecycle in one tool, from project scaffolding through evaluation, deployment, and Gemini Enterprise registration, so teams do not stitch together separate steps.
  • Works standalone from the terminal as well, so the same scaffold, eval, and deploy commands run without a coding agent in the loop.

under the hood

  • Wraps Google's Agent Development Kit (ADK); the CLI supplies skills and tools while ADK provides the underlying agent framework.
  • Primarily Python (requires Python 3.11+, the uv package manager, and Node.js), with infrastructure defined in HCL and smaller amounts of Go, Java, and TypeScript.
  • Evaluation generates traces by running agents against datasets and grades them by metric, while deployment provisions to Agent Runtime, Cloud Run, or GKE with CI/CD and RAG datastore setup.

Radar summary, generated from the project's public sources

star history

PR#37 · 4k6k now Apr 2026Aug 2026
  1. PR#37 4k 2026-07-01
  2. now 6k + 2k since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Better known than its recent output, coasting a little on attention.

-11 understory score output 60 · clout 71
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#37 2026-07-01 below the radar

    A skill suite that teaches a coding agent to build other agents

similar projects

compare these →
  • 🧠 LangGraph

    7× the stars

    Build resilient agents.

    40k ACTIVE
  • 🖼️ Langflow

    27× the stars

    Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

    153k ACTIVE
  • 📚 Haystack

    4.6× the stars

    Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

    26k ACTIVE

comments

Sign in with GitHub to add your blip on agents-cli.

loading comments…