convex-agents

Build persistent, stateful AI agents with Convex including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration. Before implementing, do not assume; fetch the latest documentation: Define tools that agents can use: - Primary: - Convex Agent Component: - For broader context: - 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 - 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 - Not persisting threads - Conversations lost on refresh - Blocking on long responses - Use streaming instead - Tool errors crashing agents - Add proper error handling - Large context windows - Summarize old messages - Missing embeddings for RAG - Generate embeddings on insert - Convex Documentation: - Convex LLMs.txt: - Convex AI: - Agent...