convex-agents

Build persistent, stateful AI agents with thread management and tool integration.

Updated Feb 8, 2026
One-click install
npx skills add https://github.com/Pratikkadam254/LinkedinLeadGen --skill convex-agents-pratikkadam254
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: convex-agents
Source: https://github.com/Pratikkadam254/LinkedinLeadGen/tree/main/.claude/skills/convex-agents
Command: npx skills add https://github.com/Pratikkadam254/LinkedinLeadGen --skill convex-agents-pratikkadam254

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Convex Agents enable building persistent, stateful AI agents with thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration.

Core Features & Use Cases

  • Persistent State: Conversation history survives restarts across sessions and devices.
  • Streaming Responses: Real-time AI outputs to clients as tokens are produced.
  • Tool Execution & Orchestration: Use Convex functions as agent tools and coordinate durable workflows for long-running tasks.
  • RAG & Knowledge Retrieval: Integrate vector search and retrieval-augmented generation for contextual answers.
  • Use Case: Build a customer support agent that preserves context, suggests actions, and triggers background workflows.

Quick Start

Create an agent instance with a configured toolset and start a chat workflow.

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 with conversation history that survives restarts?

Persistent AI agents maintain conversation history across sessions and devices by leveraging stateful backend environments. Convex Agents provide thread management and durable storage, ensuring context survives restarts for continuous chat and automation workflows.

How do I stream AI responses to clients in real-time during chat workflows?

Streaming AI responses deliver tokens to clients immediately as the model produces them. Convex Agents enable real-time output streaming directly within chat workflows, reducing latency and improving user experience for interactive applications.

Can I use Convex functions as tools for AI agent orchestration?

Convex functions can be defined and integrated as executable tools for AI agents. This allows agents to orchestrate complex operations, trigger background workflows, and coordinate long-running tasks directly within the Convex environment.

How do I implement retrieval augmented generation in a stateful agent backend?

Retrieval augmented generation in a stateful backend combines vector search with conversation history to provide contextual answers. Convex Agents integrate vector search capabilities, enabling knowledge retrieval and contextual responses within persistent threads.

What is the best way to manage long-running tasks in AI automation workflows?

Managing long-running tasks requires durable workflow orchestration that maintains state during execution. Convex Agents coordinate durable workflows, allowing AI automations to execute reliably across extended periods without losing progress or context.

Does this approach work for building customer support agents that trigger background actions?

Building customer support agents with background action capabilities requires persistent context and tool orchestration. Convex Agents support this by preserving conversation history, suggesting actions, and triggering durable workflows for automated resolution.