Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration

Convex Agents Build persistent, stateful AI agents with Convex including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration. Documentation Sources Before implementing, do not assume; fetch the latest documentation: Primary: https://docs.convex.dev/ai Convex Agent Component: https://www.npmjs.com/package/@convex dev/agent For broader context: https://docs.convex.dev/llms.txt Instructions Why Convex for AI Agents Persistent State Conversation history survives restarts Real time Updates Stream responses to clients automatically Tool Execution Run Convex functions as agent tools Durable Workflows Long running agent tasks with reliability Built in RAG Vector search for knowledge retrieval Setting Up Convex Agent Thread Management Sending Messages and Streaming Responses Tool Integration Define tools that agents can use: Agent with Tools RAG (Retrieval Augmented Generation) Workflow Orchestration Examples Complete Chat Application Schema React Chat Component Best Practices Never run npx convex deploy unless explicitly instructed Never run any git commands unless explicitly instructed Store conversation history in Convex for persistence Use streaming for better user experience with long responses Implement proper error handling for tool failures Use vector indexes for efficient RAG retrieval Rate limit agent interactions to control costs Log tool usage for debugging and analytics Common Pitfalls 1. Not persisting threads Conversations lost on refresh 2. Blocking on long responses Use streaming instead 3. Tool errors crashing agents Add proper error handling 4. Large context windows Summarize old messages 5. Missing embeddings for RAG Generate embeddings on insert References Convex Documentation: https://docs.convex.dev/ Convex LLMs.txt: https://docs.convex.dev/llms.txt Convex AI: https://docs.convex.dev/ai Agent Component: https://www.npmjs.com/package/@convex dev/agent

convex-agents