Features
Adaptive RAG-powered memory with hybrid search and knowledge graph
Chat via Telegram, Slack, Teams, or webhook API
Custom personality (name, language, tone)
Task management with priorities, due dates, and proactive reminders
Smart reminders and recurring actions in natural language
Expert Agents for delegated complex tasks
MCP skills catalog with 70+ pre-built integrations installed via chat
Google Services OAuth2 integration (Gmail, Calendar, Analytics, Ads)
Web search (SearXNG), clean page reading (Crawl4AI), and browser automation (Chromium)
Voice transcription, photo analysis, document extraction, file downloads
Smart background checks with silent monitoring
Project memory via persistent markdown documents
OpenClaw integration for autonomous coding tasks
Support for 8 LLM providers (Claude, GPT, Gemini, Mistral, DeepSeek, Ollama, OpenRouter, OpenAI-compatible)
Self-hosted with one setup script, no cloud lock-in
No-code visual workflow builder
Omnichannel deployment (web, phone, mobile)
Low-latency voice (500ms)
High throughput (300k messages/min)
Integrated prototyping and NLU modeling
Entry conditions for playbooks/workflows
Required variables for workflows
Organization-level usage breakdown
Voiceflow Core optimized model (May 2026)
Transcript filtering by workflow and tool
