convex-agents

Develop AI agents with persistent state, real-time updates, and tool integration.

23|5|Updated Nov 5, 2025
One-click install
npx skills add https://github.com/J-StaR-Films-Studios/VibeCode-Protocol-Suite --skill convex-agents-j-star-films-studios
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: convex-agents
Source: https://github.com/J-StaR-Films-Studios/VibeCode-Protocol-Suite/tree/main/assets/.agent/skills/convex-agents
Command: npx skills add https://github.com/J-StaR-Films-Studios/VibeCode-Protocol-Suite --skill convex-agents-j-star-films-studios

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @convex-dev/agent, ai, openai, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill addresses the challenge of creating complex AI agents with persistent state, real-time updates, and integrated tools for efficient AI workflows.

Core Features & Use Cases

  • Persistent State: Maintain conversation history across restarts.
  • Real-time Updates: Stream responses to clients automatically.
  • Tool Integration: Run Convex functions as agent tools.
  • RAG Patterns: Built-in vector search for knowledge retrieval.
  • Use Case: Develop a chatbot that maintains a user's profile and context across sessions, integrates with external tools for data retrieval, and generates responses based on real-time information.

Quick Start

Use the convex-agents skill to create a new AI agent with persistent state and real-time updates.

Frequently Asked Questions about convex-agents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build AI agents with persistent state across sessions?

To build AI agents with persistent state, you need a framework that maintains conversation history across restarts. This Skill uses Convex to provide persistent state, allowing chatbots and virtual assistants to retain user context and profile data seamlessly.

What's the best way to integrate tool calling into a Convex AI application?

The best way to integrate tool calling in a Convex AI application is to run Convex functions directly as agent tools. This allows your AI agents to execute backend logic and fetch real-time data dynamically during their workflows.

How do I implement RAG patterns for knowledge retrieval in an AI chatbot?

You can implement RAG patterns for knowledge retrieval by utilizing built-in vector search capabilities. This allows your AI agents to search and retrieve relevant information from a knowledge base to generate contextually accurate responses.

Can I stream real-time updates from AI agents to clients automatically?

Yes, you can stream real-time updates from AI agents to clients automatically. This Skill enables automatic response streaming, ensuring that clients receive AI-generated outputs instantly as they are processed.

Do I need OpenAI and Convex to build agents with thread management?

Yes, you need OpenAI for AI model access and Convex for backend infrastructure to build agents with thread management. These dependencies provide the necessary foundation for managing complex agent workflows and conversation threads.