Google releases Gemini API CLI for existing agents to call the Gemini API
Google has released the Gemini API CLI, a command-line tool for calling the Gemini API that can be handed to existing agents such as Claude Code, Codex, and Cursor. It supports generating images, video, speech, and music; analyzing PDFs, images, audio, video, and YouTube URLs; transcribing recordings into md, json, or srt; and running Deep Research in the background. The tool is stateless, with no memory or chat mode—context and planning are handled by the agent—and it supports self-describing parameters such as --help and --dry-run.
Why read this
AI score 57
The original text explains the CLI's stateless design and how it hands context to existing agents, so readers can judge whether it can fit into their own workflows.
Topics
Body
We launched the Gemini API CLI. A CLI for calling the Gemini API. Give it to the agent you already use (Claude Code, Codex, Antigravity, Cursor, OpenClaw, Hermes...). It's NOT a new coding agent you can use it too:
1. Generate images, video, speech, music. 2. Analyze PDFs, images, audio, video, YouTube URLs, 3. Transcribe recordings to md / json / srt, 4. Run Deep Research in the background.
Stateless. No memory, no chat mode. Your agent owns the context and the plan, gemini-api does the API call. Build for Agents, it's self-describing. `--help`, `--dry-run`...
Start here: https://t.co/D812RdijJO