Philipp Schmid· @_philschmid · X·· 2 小时前AI 评分64
AI 导读
Google 发布了 Gemini API CLI，这是一个无状态的命令行工具，可供现有 Claude Code、Cursor 等 Agent 直接调用以完成多模态生成、文件分析及后台 Deep Research。该工具不包含记忆或聊天模式，由调用方 Agent 负责上下文与规划，并通过自描述特性提供帮助与预演能力。
正文 · 原文
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:
- Generate images, video, speech, music.
- Analyze PDFs, images, audio, video, YouTube URLs,
- Transcribe recordings to md / json / srt,
- 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://aistudio.google.com/learn/introducing-the-gemini-api-cli?e=0
来源：Philipp Schmid · x.com