Open source integration layer for AI agents with secure, multi-tenant support
Your phone as an API for SMS, calls, recordings and transcripts
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
NO
Pricing model
Freemium
Paid
Pricing
Hobby: $0/mo with up to 50 connections, 100k webhook events, unlimited managed permissions/auth pages, up to 3 team members, and Discord community support. Pro: $200/mo with unlimited connections, unlimited webhook events, unlimited managed permissions/auth pages, unlimited team members, and Slack s
Monthly subscription per connected line (exact price not specified in documentation). Recording and transcription are optional, charged from prepaid credits at rates shown in workspace. Credits are in US dollars and never expire while workspace is active.
Key features
OAuth and multi-tenant credential management
Permissions system with approval workflows
Webhooks and polling for data synchronization
Multiple integration connectors
Self-hosted and cloud-hosted options
Managed authentication pages
Agent-safe credential handling
API caching per tenant
Custom integration scaffolding
Community-contributed integrations
Send SMS messages up to 1,600 characters
Receive incoming SMS and calls as webhook events
Outgoing calls with WebRTC audio for browser or AI
Idempotent messaging with operation status tracking
Model Context Protocol server for Claude and Cursor
Included bridge minutes per month
Conversation scoping per line and number
API rate limiting and fair-use enforcement
Dual-SIM support with separate credentials per line
What makes it different
Fully open source to avoid vendor lock-in
Credentials never stored in Corsair's database
Free self-hosted option with no per-seat pricing
Handles token refresh and API deprecations automatically
Works with or without AI agents
Use your own Android phone and SIM instead of a phone number service
Pay only per connected line; recording and transcription are optional and prepaid
Calls merged on bridge preserve your business number to recipients
Live AI voice support via WebRTC audio tracks
Every resource reports whether it is real or simulated