convex-agents

Develop AI agents on Convex with text generation, RAG, and vector search.

Updated Mar 17, 2026
One-click install
npx skills add https://github.com/roynulrohan/convex-skills --skill convex-agents-roynulrohan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: convex-agents
Source: https://github.com/roynulrohan/convex-skills/tree/main/skills/convex-agents
Command: npx skills add https://github.com/roynulrohan/convex-skills --skill convex-agents-roynulrohan

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of building and managing AI agents on Convex, providing tools for chatbots, AI assistants, and other AI-powered functionalities.

Core Features & Use Cases

  • Agent Class & Tools: Utilize the @convex-dev/agent component to create agents with language models, tools, and thread management.
  • Text & Object Generation: Generate text and structured objects with AI models, including streaming and asynchronous capabilities.
  • RAG & Vector Search: Integrate Retrieval-Augmented Generation and vector search for enhanced AI agent capabilities.
  • Use Case: Develop a chatbot that can handle customer inquiries by integrating with external knowledge bases and AI models.

Quick Start

Start by setting up the @convex-dev/agent component and define an agent with a language model and tools.

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 on Convex for chatbots and AI assistants?

You can build AI agents on Convex by using the @convex-dev/agent component to define agent classes with language models, tools, and thread management. This allows you to create chatbots and AI assistants with text generation and streaming capabilities.

Can I use OpenAI, Anthropic, and Google AI models with Convex agents?

Yes, Convex agents support OpenAI, Anthropic, and Google AI models. The skill integrates the respective AI SDKs to let you define agents with various language models for text and structured object generation.

How do I add RAG and vector search to a Convex AI agent?

You can add Retrieval-Augmented Generation and vector search by utilizing the @convex-dev/agent component. This integration enhances AI agent capabilities by allowing them to query external knowledge bases during text generation.

What is needed to set up AI agent management on Convex?

Setting up AI agent management requires a Convex environment, the @convex-dev/agent component, and relevant AI SDKs. You start by configuring the component and defining an agent with a chosen language model and tools.

Does the Convex agent component support asynchronous text and object generation?

Yes, the Convex agent component supports generating text and structured objects asynchronously. This includes streaming capabilities to handle AI model responses efficiently for chatbots and AI assistants.

How do I manage conversation threads for AI assistants on Convex?

You manage conversation threads using the thread management features within the @convex-dev/agent component. This allows your AI assistants to maintain context across multiple interactions and handle customer inquiries effectively.