Google 发布 Gemini API CLI,供现有智能体调用 Gemini API
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, Herme
Google 发布 Gemini API CLI,这是一个用于调用 Gemini API 的命令行工具,可交给 Claude Code、Codex、Cursor 等现有智能体使用。它支持生成图像、视频、语音和音乐,分析 PDF、图片、音频、视频及 YouTube URL,把录音转写为 md、json 或 srt,并在后台运行 Deep Research。该工具无状态,没有记忆和聊天模式,上下文与计划由智能体掌握,并支持 --help、--dry-run 等自描述参数。
推荐理由
AI 评分 57
原文说明了这个 CLI 的无状态设计,以及它如何把上下文交给现有智能体,读者可据此判断它能否接入自己的工作流。
主题
正文
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:
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