Skip to main content
Glama
backspacevenkat

polydev-ai

Polydev Plugin for Claude Code

πŸš€ Multi-model AI consultation for Claude Code - Get perspectives from Claude, GPT, Gemini, Grok, and Z AI in your IDE.

SWE-bench License: MIT

What is Polydev?

Polydev lets you consult multiple AI models simultaneously when you're stuck on bugs, making architecture decisions, or reviewing code. Different models catch different things - combining their perspectives eliminates blind spots.

Stop copy-pasting your code into ChatGPT, Claude, Gemini, Grok... Get all their perspectives in your IDE with one request.

Research: Achieved 74.6% on SWE-bench Verified, matching Claude Opus at 62% lower cost.

Related MCP server: multi-ai-collab

Installation

# Add the Polydev marketplace
/plugin marketplace add backspacevenkat/polydev-claude-code-plugin

# Install the plugin
/plugin install polydev

Setup

  1. Get your free token at polydev.ai/dashboard

    • 1,000 messages/month free

    • No credit card required

  2. Add token to your environment:

    export POLYDEV_USER_TOKEN="pd_your-token-here"
  3. Restart Claude Code and verify with /mcp

Usage

Slash Commands

Command

Description

/perspectives

Get multi-model perspectives on current problem

/polydev-help

Show setup guide

Natural Language

Just ask Claude - it will automatically invoke Polydev when appropriate:

"I'm stuck on this authentication bug. Get different perspectives."

"Should I use Redis or PostgreSQL for session storage?"

"Review this API endpoint for security issues using polydev."

Auto-Invocation

The plugin automatically triggers multi-model consultation when you:

  • Say you're "stuck" or "confused"

  • Ask comparison questions ("Should I use X or Y?")

  • Request code reviews or security checks

  • Have multiple failed debugging attempts

Models Available

Polydev queries multiple leading AI models simultaneously:

Model

Provider

Claude

Anthropic

GPT

OpenAI

Gemini

Google

Grok

xAI

Z AI

Zhipu

Example Output

πŸ€– Multi-Model Analysis

Claude's Perspective:
The N+1 query pattern here is causing performance issues...

GPT's Perspective:
The infinite re-render is likely caused by object recreation in deps array...

Gemini's Perspective:
Check for setState calls directly in the component body...

Grok's Perspective:
Consider using useCallback for function dependencies...

βœ… Consensus: All models agree the issue is in the dependency array
πŸ’‘ Recommendation: Use useMemo/useCallback for object/function deps

License

MIT License - see LICENSE

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    Not graded
    maintenance
    Orchestrates multiple AI models (Gemini, OpenAI, Claude, local models) within a single conversation context, enabling collaborative workflows like multi-model code reviews, consensus building, and CLI-to-CLI bridging for specialized tasks.
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    Queries multiple AI models simultaneously (GPT 5.2, Claude Opus 4.5, Gemini 3, Grok 4.1) via a single API call to provide diverse expert perspectives and consensus recommendations.
    MIT
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables a primary AI coding assistant to delegate tasks to multiple specialized CLI agents (such as Gemini, Claude, Codex, and Cursor) in parallel from a single prompt, sharing project context across all of them. It aggregates their outputs into one synthesized response while relying on the user's existing CLI tools and subscriptions.
    -