polydev-ai
Query multiple AI models (GPT-4, Claude, Gemini, Grok) in parallel for diverse perspectives. Get different expert viewpoints when stuck or need enhanced reasoning.
README
Polydev Plugin for Claude Code
š Multi-model AI consultation for Claude Code - Get perspectives from Claude, GPT, Gemini, Grok, and Z AI in your IDE.
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.
Installation
# Add the Polydev marketplace
/plugin marketplace add backspacevenkat/polydev-claude-code-plugin
# Install the plugin
/plugin install polydev
Setup
-
Get your free token at polydev.ai/dashboard
- 1,000 messages/month free
- No credit card required
-
Add token to your environment:
export POLYDEV_USER_TOKEN="pd_your-token-here" -
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 | |
| Grok | xAI |
| Z AI | Zhipu |
Example Output
š¤ 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...
ā
Consensus: All models agree the issue is in the dependency array
š” Recommendation: Use useMemo/useCallback for object/function deps
Links
- š Polydev Website
- š Research Paper
- š Claude Code Guide
- š¬ Support
License
MIT License - see LICENSE
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.