Human CLI

Multimodal CLI and MCP server for vision, image generation, text-to-speech, and reasoning via Google Gemini.

mrgoonie 29 ↓ 108
Claude CodeClaude DesktopGeneric
View source ↗

Human CLI is a terminal tool with an optional MCP server providing multimodal AI capabilities powered by Google Gemini. Offers image analysis and document reading, image generation and editing with inpainting and style transfer, text-to-speech narration, and reasoning tools. Available as an npm package and invocable as an MCP server via the human mcp start command.

Source

Repository: https://github.com/mrgoonie/human-cli

Maintain Human CLI?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[Human CLI on getagentictools](https://getagentictools.com/mcp/mrgoonie-human-cli?ref=badge)