agents-cli vs squid
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 — Claude Code plugin that turns a feature spec into a reviewed PR through a 5-agent pipeline — PA → SWE → Tester → PR-Reviewer → On-Call — with exactly two human gates.
Same shape — a skills layer that upgrades your coding assistant into a specialized workflow — different bet: agents-cli specializes it for the Google Cloud agent lifecycle; squid for a convention-enforcing spec→PR software factory.
| agents-cli | squid | |
|---|---|---|
| Stars | 5.2k | 136 |
| Forks | 542 | 20 |
| Language | Python | Shell |
| License | Apache-2.0 | Apache-2.0 |
| Last activity | 6 days ago | 4 days ago |
| Topics | coding, evals, skills | coding, orchestration |
| Curated connections | 5 | 6 |
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.
squid — the curator's take
Squid is for people who already live in Claude Code and are tired of re-explaining team conventions every session: markdown specs + five adversarial agents (no agent both writes code and judges it) turn a spec into a PR while you only show up to approve the plan and merge. When NOT: you don't use Claude Code (it's a plugin, not a standalone tool), your stack is Rust/Java/mobile (specs are Python/TS/Go for now), or you already trust an in-house pipeline. Early days and opinionated by design — adopt the opinions or skip it.