Promptheus

Created By

abhichandra216 days ago

AI-powered prompt refinement tool with adaptive questioning and multi-provider support. Provides 5 MCP tools (refine_prompt, tweak_prompt, list_models, list_providers, validate_environment) for intelligent prompt engineering. Supports Google Gemini, Anthropic Claude, OpenAI, Groq, Alibaba Qwen, and Zhipu GLM. Features adaptive task detection, interactive/structured modes, and session history management.

# prompt-engineering

# ai

Overview Content Tools Comments

Overview

What is Promptheus?

Promptheus is an AI-powered prompt refinement tool designed to enhance and optimize prompts for large language models (LLMs) through adaptive questioning and multi-provider support.

How to use Promptheus?

To use Promptheus, install it via pip with pip install promptheus, then run it in an interactive session or use the command line to refine prompts directly. You can also access a web interface for a more user-friendly experience.

Key features of Promptheus?

Adaptive questioning for prompt refinement
Multi-provider support including Google Gemini, OpenAI, and Anthropic Claude
Interactive refinement through natural conversation
Session history management for tracking and reusing past prompts
CLI and web UI for flexible usage

Use cases of Promptheus?

Generating content such as blog posts or articles with specific requirements.
Analyzing and improving code snippets for security or performance.
Integrating into pipelines for automated prompt processing.

FAQ from Promptheus?

Can Promptheus work with multiple AI providers?

Yes! Promptheus supports various providers like Google, OpenAI, and Anthropic.

Is there a web interface available?

Yes! Promptheus includes a web UI for interactive prompt refinement.

How does adaptive questioning work?

It intelligently detects what information is needed to refine prompts effectively.

Server Config

{
  "mcpServers": {
    "promptheus": {
      "type": "stdio",
      "command": "~/Promptheus/venv/bin/python",
      "args": [
        "-m",
        "promptheus.main",
        "mcp"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "API-KEY"
      }
    }
  }
}

Recommend Servers

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

Howtocook Mcp基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

ChatWiseThe second fastest AI chatbot™

MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

Tavily Mcp

WindsurfThe new purpose-built IDE to harness magic

CursorThe AI Code Editor

Baidu Map百度地图核心API现已全面兼容MCP协议，是国内首家兼容MCP协议的地图服务商。

MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs

Serper MCP ServerA Serper MCP Server