Back to directory

agents-cli

A CLI and set of skills that teach a coding assistant to build, evaluate, and deploy AI agents on Google's Gemini Enterprise Agent Platform.

agents-cli

agents-cli adds Google Cloud agent-building skills to whichever coding assistant a developer is already using, such as Antigravity CLI, Claude Code, or Codex, rather than requiring them to learn each underlying Google Cloud service and CLI directly. Its skills cover the development lifecycle and model selection, the ADK Python API for agents, tools, orchestration, and callbacks, project scaffolding, evaluation with metrics and LLM-as-judge grading, deployment to Agent Runtime, Cloud Run, or GKE with CI/CD, publishing to Gemini Enterprise, and observability through Cloud Trace and logging.

A companion CLI provides direct commands for the same operations, including creating a new agent project, running the evaluation dataset and grading traces, deploying to Google Cloud, and registering with Gemini Enterprise. It can be installed fully with uvx, or as just the skills through the skills package manager.

It requires Python 3.11 or newer, uv, and Node.js, and is written in Python under the Apache-2.0 license.

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.