skills.rest
Yahia89
Yahia89COMMUNITY
Explore all skills by this author →
GitHub

convex-agents

Create persistent, stateful AI agents with thread management and streaming in Convex.

Updated Apr 7, 2026
Search Tags:#ai#llm#rag#agents#tools#workflows#convex
One-click install
npx skills add https://github.com/Yahia89/ordering-food --skill convex-agents-yahia89
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: convex-agents
Source: https://github.com/Yahia89/ordering-food/tree/main/.claude/skills/convex-agents
Command: npx skills add https://github.com/Yahia89/ordering-food --skill convex-agents-yahia89

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Builds and coordinates persistent, stateful AI agents that can manage long-running tasks, maintain conversation context, and orchestrate tools and services without losing progress across restarts.

Core Features & Use Cases

  • Persistent State: Agents retain conversation history and context across sessions.
  • Streaming Responses: Real-time token streaming to clients for responsive interactions.
  • Tool Integration & Orchestration: Run Convex functions as agent tools and compose multi-step workflows.
  • RAG & Knowledge Workflows: Integrate retrieval-augmented patterns for knowledge access and decision making.
  • Workflow Orchestration: Coordinate complex, durable processes that span multiple steps and services.
  • Use Cases: Personal assistants, customer support agents, and research assistants that need reliability and extensibility.

Quick Start

Set up a basic Convex Agent project and run a chat example to verify threading, streaming, and tool usage.

Frequently Asked Questions about convex-agents

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

FAQPage Schema
How do I maintain conversation context for AI agents across server restarts?▼

Persistent state for AI agents is maintained by storing conversation history and context in a Convex environment. This allows agents to retain progress and resume long-running workflows seamlessly across sessions.

How do I stream AI agent responses in real-time to clients?▼

Real-time token streaming is enabled natively for AI agents within the Convex environment. This provides responsive client interactions by pushing tokens directly as they are generated during the workflow.

Can I use Convex functions as tools for RAG-enabled AI agents?▼

Yes, you can run Convex functions as agent tools. This enables tool integration and orchestration for retrieval-augmented generation (RAG) workflows, allowing agents to access knowledge and execute multi-step tasks.

What is the best way to orchestrate multi-step agent workflows without losing progress?▼

Orchestrating complex, durable processes that span multiple steps and services is best handled using persistent state with thread management. This ensures agents coordinate long-running tasks without losing progress.

Do I need a specific environment setup to manage long-running AI agent tasks?▼

Yes, you need a Convex environment and the Convex Agent component to wire up agents, threads, and tool integrations. This setup is required to manage long-running tasks and maintain conversation context.

Why does my stateful AI agent lose its conversation history between sessions?▼

Stateful AI agents lose conversation history without persistent state management. Implementing thread management within a Convex environment ensures conversation context is retained across sessions.

Related Skills

Explore More Software Engineering Skills→
robertgussrobertguss
7

convex-quickstart

...

Community
Advanced
ThinkOffAppThinkOffApp
42

ide-agent-kit

Coordinate multi-agent IDE workflows across local files, webhooks, and shells.

Community
Advanced
Godhand-ArnavGodhand-Arnav

rag-architect

Design and implement end-to-end RAG pipelines for context-aware LLM responses.

Community
Advanced
EricJamesCrowEricJamesCrow

convex-agents

Build persistent, stateful AI agents with tool hooks and streaming in Convex.

Community
Advanced