convex-agents

Develop persistent AI agents with stateful memory across restarts.

Updated Mar 6, 2026
One-click install
npx skills add https://github.com/mmtftr/bakathon --skill convex-agents-mmtftr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: convex-agents
Source: https://github.com/mmtftr/bakathon/tree/main/.opencode/skills/convex-agents
Command: npx skills add https://github.com/mmtftr/bakathon --skill convex-agents-mmtftr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Convex Agents enables developers to build persistent AI agents with stateful memory, tool integration, streaming responses, and durable workflows for complex, long-running tasks.

Core Features & Use Cases

  • Persistent state across restarts and real-time updates for agent interactions
  • Tool integration, streaming responses, and durable workflows
  • Use cases include customer support chatbots, internal automation agents, and research assistants

Quick Start

Install the Convex Agent package and create an initial agent using your preferred OpenAI model to start a threaded conversation.

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 retain conversation state across restarts?

You build persistent AI agents that retain conversation state across restarts by applying the Convex Agents framework, which supports durable workflows and thread management for real-time chat assistants and long-running tasks.

What is the best way to manage streaming responses and tool integration for stateful AI agents?

The best way to manage streaming responses and tool integration for stateful AI agents is using a backend framework like Convex, which enables durable workflows and persistent state for complex agent interactions.

Can I use Convex to create long-running workflows for customer support chatbots?

Yes, you can use Convex to create long-running workflows for customer support chatbots, as it provides durable workflow execution, real-time updates, and persistent memory across software restarts.

How do I implement RAG-style knowledge retrieval in an AI agent?

You implement RAG-style knowledge retrieval in an AI agent by utilizing a stateful framework like Convex Agents, which supports thread management and tool integration to retrieve and maintain knowledge context.

Does this approach work for internal automation agents and research assistants?

Yes, this approach works for internal automation agents and research assistants, providing durable workflows and tool integration to handle complex tasks across software development and research contexts.