convex-agents

Develop stateful AI agents with the Convex Agent component for threads, tools, and streaming.

Updated Feb 21, 2026
One-click install
npx skills add https://github.com/mikeyfennelly1/hackeurope--210226 --skill convex-agents-mikeyfennelly1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: convex-agents
Source: https://github.com/mikeyfennelly1/hackeurope--210226/tree/main/.agents/skills/convex-agents
Command: npx skills add https://github.com/mikeyfennelly1/hackeurope--210226 --skill convex-agents-mikeyfennelly1

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill simplifies the creation of sophisticated AI agents by providing a robust framework for managing state, integrating tools, and orchestrating complex workflows within the Convex real-time database.

Core Features & Use Cases

  • Persistent State Management: Agents maintain conversation history and context across sessions.
  • Tool Integration: Seamlessly connect agents to external functions and APIs.
  • RAG & Workflow Orchestration: Implement advanced patterns like Retrieval Augmented Generation and multi-step processes.
  • Use Case: Develop a customer support agent that can access a knowledge base, create support tickets, and provide real-time, streaming answers to user queries.

Quick Start

Install the necessary packages and set up the Convex agent component in your Convex project.

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 history?

Build stateful AI agents by using the Convex Agent component to manage conversation threads and maintain persistent context across sessions within the Convex real-time database.

How do I orchestrate RAG and multi-step workflows for AI agents?

Orchestrate RAG and multi-step workflows by utilizing the Convex Agent component to coordinate retrieval augmented generation patterns and execute durable, multi-step processes within your Convex project.

Can I stream real-time AI agent responses using Convex?

Yes, you can stream real-time AI agent responses using the Convex Agent component, which supports real-time updates and streaming outputs directly within the Convex ecosystem.

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

Integrate external tools and APIs into Convex AI agents by connecting your functions to the Convex Agent component, enabling seamless tool execution and orchestration alongside your database workflows.

Do I need the OpenAI SDK to build agents with the Convex Agent component?

Yes, building agents with the Convex Agent component requires installing the OpenAI SDK alongside the Convex Agent package to handle underlying LLM interactions and tool integrations.