Credentials. Keep the API key in your shell environment, not in the repo.
Who it is forA developer joining an unfamiliar project who needs the big picture fast.
The problemReading a new codebase file by file takes days.
The outcomeA plain-language summary of the architecture and where the key pieces live.
What you need first
- Node.js (npm), Homebrew, MacPorts or conda
- A Gemini API key from AI Studio or a Google Cloud project for Vertex AI
Steps
- Try it without installing:
npx @google/gemini-cli, or install withnpm install -g @google/gemini-cliorbrew install gemini-cli - Set your key:
export GEMINI_API_KEY="YOUR_API_KEY" - In the repo run
gemini, and add sibling folders withgemini --include-directories ../lib,../docs - Ask it to explain the architecture or summarize recent changes
Prompt for your agent
In this repo, run google-gemini/gemini-cli with my GEMINI_API_KEY from the environment and ask it to explain the architecture, the entry points and the riskiest module. Paste its answer in a file ARCHITECTURE_NOTES.md.
Caveat. Unpaid tier and Google One users were moved to Antigravity CLI on June 18, 2026; this path needs an API key or Vertex AI.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for google-gemini/gemini-cli and "Ask Gemini to explain a codebase from the terminal"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer