Features
Multi-turn conversational assistants with session management
Retrieval-Augmented Generation (RAG) with built-in vector stores
Supports OpenAI, Anthropic, Google, and local models via LiteLLM
Django admin integration for managing assistants and data sources
Key-value and summary memory types for conversations
File upload and processing for context injection
Streaming response support
Built-in vector store backends: Chroma, Pinecone, Qdrant, PGVector
Tool/function calling integration with Django ORM
Customizable system prompts and assistant personality
Conversation history persistence via Django models
Asynchronous support for high-concurrency scenarios
Performance trace recording and insights
Network request analysis and inspection
Console message reading with source-mapped stack traces
Puppeteer-based automation with auto-wait
Slim mode for basic browser tasks
CLI usage without MCP client
Optional CrUX API integration for field data
Usage statistics with opt-out
Update checks via npm (configurable)
Multi-account Chrome support
Gemini integration via extension
Source-mapped stack traces in console output
Auto-wait for action results
