skills.rest
waynesutton
waynesuttonCOMMUNITY
Explore all skills by this author →
Website𝕏@waynesuttonGitHub

convex-agents

Build persistent AI agents with Convex components for stateful conversations.

401|32|Updated Jan 14, 2026
Search Tags:#ai#rag#tooling#agent#streaming#workflows#convex
One-click install
npx skills add https://github.com/waynesutton/convexskills --skill convex-agents-waynesutton
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: convex-agents
Source: https://github.com/waynesutton/convexskills/tree/main/skills/convex-agents
Command: npx skills add https://github.com/waynesutton/convexskills --skill convex-agents-waynesutton

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Convex Agents enable developers to build persistent, stateful AI agents that can manage long-running conversations, integrate with tools, stream responses, and orchestrate complex workflows.

Core Features & Use Cases

  • Persistent state: Conversations and context survive restarts.
  • Real-time streaming: Stream responses to clients as tasks progress.
  • Tool execution: Run Convex functions and external tools to perform actions.
  • Durable workflows: Long-running tasks with reliability and fault tolerance.
  • Built-in RAG: Vector search for knowledge retrieval and synthesis.

Quick Start

Install the Convex Agent package and follow the examples to scaffold an initial agent.

Frequently Asked Questions about convex-agents

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

FAQPage Schema
How do I build persistent AI agents that survive application restarts?▼

Persistent AI agents maintain stateful conversations and context across restarts by integrating with Convex components. This ensures long-running workflows and thread management remain durable without losing previous interactions.

What is the best way to stream AI agent responses in real-time to clients?▼

Real-time streaming for AI agents sends responses to clients as tasks progress. Using the Convex agent library, developers can stream outputs directly while executing long-running tool actions in the background.

How do I add RAG knowledge retrieval to a stateful AI agent?▼

Add RAG knowledge retrieval to an AI agent using built-in vector search capabilities. This allows the agent to synthesize context and retrieve relevant information from stored data during stateful conversations.

Can I execute external tools and Convex functions within an AI workflow?▼

You can execute external tools and run Convex functions within an AI workflow to perform actions. Tool execution enables the agent to interact with external systems and orchestrate complex, fault-tolerant tasks.

Does Convex support durable workflows for long-running AI tasks?▼

Convex supports durable workflows for long-running AI tasks with reliability and fault tolerance. This ensures that complex agent actions and tool executions complete successfully even during system failures.

Related Skills

Explore More Software Engineering Skills→
JStaRFilmsJStaRFilms
23

convex-agents

Configure persistent, stateful AI agents with the Convex framework.

Community
Advanced
AbrahamX3AbrahamX3
1

Convex Agents Streaming

okay, but here's the thing: I'm going to need you to get a lot more specific before I can write your code.

Community
Intermediate
jhl-labsjhl-labs
50

RAG & Vector Search

Retrieve relevant documents and augment LLM prompts with vector search.

Official
Advanced
yspreenyspreen
33

convex-agents

Build persistent, stateful AI agents with Convex for threads, tools, and workflows.

Community
Advanced