Build, run and observe voice and chat AI agents that hold real conversations
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
TR
Pricing model
Open source
Paid
Pricing
Not given
Voice calls from $0.05 per minute, which includes a flat platform fee plus the cost of each provider used. Chat is billed per use. No seats, no contracts. Users can bring their own provider keys.
Key features
Context Ledger for curating admitted instructions, files and memory
Deterministic context admission before model processing
Workflows with Mother agent team design and checking
Love Spot drawing board with Matilda companion
Desktop app with theme customization
Support for GPT, Claude and Gemini models
Terminal and desktop app sharing state
Portable context for terminal coding agents
Voice agents for inbound and outbound calls on your own phone numbers or SIP trunk
Chat agents on your website, messaging apps (WhatsApp, Instagram, Messenger) and via API
No-code agent building with prompts or visual workflows
Calendar integration to book and cancel appointments
Knowledge base from your documents (PDF, text, Markdown, CSV, JSON)
Full conversation recording, transcript, cost breakdown and step-by-step timeline
Call transfer to people and live call monitoring from dashboard
Support for multiple AI models and voice providers
Outbound campaigns with calling hours and do-not-call protection
Automated post-call analysis and structured data extraction
What makes it different
Deterministic context admission ensures agents see processed context before model receives it
Context Ledger provides transparent curation of agent inputs
Mother agent orchestrates multi-agent workflows with checking and merged results
Collaborative drawing interface with AI companion
Bring your own AI, speech and telephony provider keys and avoid lock-in
Full audit trail with per-step cost and latency for every conversation
Version control and environments (development, staging, production)
Import agents from other platforms (Vapi, Retell, Bland, OpenAI Assistants) with no lock-in