convex-agents

Build AI agents with Convex for chat, workflows, streaming, and RAG.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/matiacone/dotfiles --skill convex-agents-matiacone
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: convex-agents
Source: https://github.com/matiacone/dotfiles/tree/main/agents/.agents/skills/convex-agents
Command: npx skills add https://github.com/matiacone/dotfiles --skill convex-agents-matiacone

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Convex Agents unifies the process of building AI agents on the Convex platform by providing an out-of-the-box toolkit for managing agents, threads, messages, streaming, tools, RAG, workflows, and React integration.

Core Features & Use Cases

  • Define agents with prompts, tools, and configurations to handle multi-turn conversations.
  • Support streaming responses, retrieval-augmented generation, and tool orchestration for dynamic workflows.
  • Integrate with React UIs to display and stream agent messages while enabling agent-driven workflows.

Quick Start

Install the agent package, configure Convex with an agent, and run the dev server to generate types and try a basic setup.

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 Convex for multi-turn chat conversations?

To build AI agents with Convex, you define agents with specific prompts, tools, and configurations to manage multi-turn conversations and orchestrate dynamic workflows.

Can I integrate streaming responses and React UIs when building AI agents in Convex?

Yes, you can integrate with React UIs to display and stream agent messages, enabling real-time streaming responses for interactive agent-driven workflows within your application.

What is the best way to add RAG capabilities to a Convex application?

The best way to add RAG is by using an out-of-the-box toolkit that supports retrieval-augmented generation, allowing you to define agents equipped with RAG-enabled tools and dynamic workflows.

How do I get started setting up an AI agent workflow in a Convex-powered app?

To set up an AI agent workflow, install the agent package, configure Convex with your agent definitions, and run the dev server to generate types and test the basic setup.

Does building AI agents with Convex require managing separate threads and messages?

Building agents with Convex provides concepts and code patterns to explicitly define and manage agents, threads, and messages, simplifying the orchestration of complex interactions.

What limitations exist when orchestrating tools and streaming interactions in Convex agents?

Convex agents support tool orchestration and streaming interactions, but implementation depth is advanced, requiring understanding of Convex workflows, React integration, and RAG configurations.