Features
Local-first, private AI assistant (no cloud dependency)
Desktop UI with streaming chat, interruption support, dark/light themes
Browser automation (multi-step control, login, click, form fill, screenshot)
File preview for PDF, Word, Excel, images, code files
Integrated terminal (node-pty + xterm, session isolation)
Smart scheduling (cron/every/once modes with visual editor and history)
Multi-channel access (Telegram, Discord, WhatsApp, Slack, email, Feishu, QQ)
Long-term memory (fact memory + history summaries, cross-session context)
Skill system (@skillname) for quick domain knowledge loading
Chrome login state reuse for authenticated web scraping
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
