convex-agents

Create persistent, stateful AI agents with the Convex Agent component.

1|Updated Feb 7, 2026
One-click install
npx skills add https://github.com/aarsh21/better-issues --skill convex-agents-aarsh21
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: convex-agents
Source: https://github.com/aarsh21/better-issues/tree/main/.agents/skills/convex-agents
Command: npx skills add https://github.com/aarsh21/better-issues --skill convex-agents-aarsh21

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill empowers developers to build sophisticated, stateful AI agents by leveraging the Convex Agent component, simplifying complex tasks like thread management, tool integration, and RAG patterns.

Core Features & Use Cases

  • Persistent Threads: Maintain conversation history across sessions.
  • Tool Integration: Connect agents to external functions and APIs.
  • RAG Patterns: Implement Retrieval Augmented Generation for knowledge retrieval.
  • Workflow Orchestration: Build multi-step agentic processes.
  • Use Case: Create a customer support agent that can access a knowledge base, create support tickets, and provide real-time answers to user queries.

Quick Start

Install the necessary packages using npm install @convex-dev/agent ai openai.

Frequently Asked Questions about convex-agents

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

FAQPage Schema
How do I build stateful AI agents with persistent conversation threads?

Build stateful AI agents with persistent conversation threads by using the Convex Agent component to maintain conversation history across sessions. It facilitates thread management and integrates with LLM providers like OpenAI for real-time responses.

What's the best way to implement RAG patterns for AI agents in a reactive backend?

Implement RAG patterns for AI agents in a reactive backend by leveraging the Convex ecosystem to handle knowledge retrieval. This Skill enables Retrieval Augmented Generation alongside workflow orchestration for multi-step processes.

How do I integrate external tools and APIs into AI agents using Convex?

Integrate external tools and APIs into AI agents using Convex by utilizing the tool integration capabilities of the Convex Agent component. This allows your agents to connect to external functions and invoke them during streaming responses.

Do I need OpenAI and specific packages to orchestrate AI agent workflows?

Yes, you need OpenAI and specific packages to orchestrate AI agent workflows. You must install @convex-dev/agent, ai, and openai via npm to enable workflow orchestration and LLM integration within the Convex ecosystem.

Can I use this approach to build a customer support agent that creates support tickets?

Yes, you can use this approach to build a customer support agent that creates support tickets. The Skill supports building agents that access a knowledge base, create tickets, and provide real-time answers to user queries.

Does workflow orchestration for AI agents work with real-time streaming responses?

Workflow orchestration for AI agents works with real-time streaming responses by utilizing Convex's reactive backend. The component facilitates building multi-step agentic processes while handling streaming outputs from LLM providers.