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
Start teams with one command and manage agents across multiple machines
Mix Claude Code, Codex and Pi agents in one team
Agents delegate and coordinate work with named task assignments and queue ownership
Agents message each other directly and read each other's screens
Restore agent conversations after restart or reboot from snapshots
Choose different models and reasoning effort per agent
Bring custom harnesses and integrate with MCP servers and Claude Desktop
Start Docker Compose services alongside agent teams
Control message filtering with typing guards and chat broadcasts
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
One conversation interface with a lead agent coordinating specialists behind the scenes
Mix multiple coding models and harnesses in one managed team
Run entirely self-hosted on your own machine with no external coordination
Open source with Apache 2.0 license and extensible harness contracts
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