Features
RAG knowledge base from URLs and file uploads (PDF, TXT, CSV, Markdown, DOCX)
Multi-model LLM agent supporting OpenAI, DeepSeek, Anthropic, Gemini, Jina, SiliconFlow
Embeddable multilingual chat widget with session persistence
SSE streaming responses for real-time answer generation
Role-based access control (super admin, admin, agent)
SSRF protection and widget origin whitelisting
Vector search using Qdrant or pgvector
Docker Compose deployment with FastAPI, Next.js, Redis, nginx
Admin console for managing knowledge, sessions, users, and site config
Self-hosted with no GPU required (inference via external APIs)
API for custom integration
Supports SQLite or PostgreSQL database
Session persistence across page reloads
Autonomous resolution of WISMO, returns, cancellations, address edits
Sales AI product page Q&A widget (up to +18% revenue per visitor)
Social AI for Facebook and Instagram DM automation (up to 60%)
75+ pre-built automations for ecommerce workflows
Real-time carrier data for order tracking updates
Brand voice consistency across all channels
Ask Yuma: conversational AI for support operation management (June 2026)
15-20 safety checks on every AI reply before sending
Confidence threshold setting for human handoff
Action-based resolution: process refunds, update addresses
Claude MCP integration for managing automations via Claude (April 2026)
First response time reduction from 24 hours to 12 minutes
Up to 89% automation rate and 63% cost savings
30-day free trial with dedicated account team setup
Gladly integration (June 2026)
