TECHNICAL PREVIEWLive PSTN calling and payments are not enabledDevelopment status

DEVELOPER REFERENCE / 25 CHAPTERS

Built to be
understood.

The developer reference for one end-to-end autonomous calling platform: agent contracts, consent, media, managed x402 research, telecoms policy, Asterisk BYOT and evidence. The 0.0.1 implementation is local and experimental, not a hosted telephone service.

START WITH THE CONTRACT

Choose your entry point.

25 chapters available

01 / REFERENCE

Overview

AI Dial-Tone 0.0.1 is an open-source agent communications development project. It is not a hosted telephone platform or a booking service. No public API exists

Read chapter →
02 / REFERENCE

Quickstart: first local AI peer session

This is a reproducible public-source example. It runs entirely on the developer's computer, uses fictional actors and does not dial a telephone number. You do n

Read chapter →
03 / REFERENCE

Architecture

AI Dial-Tone 0.0.1 separates trusted operator control, two untrusted bot peers, and media/events over localhost. This does not yet connect to a carrier or a PBX

Read chapter →
04 / REFERENCE

Authentication and permissions

The runnable Peer Lab uses three distinct bearer authorities. These are local test credentials, not real customer identities or legally sufficient human consent

Read chapter →
05 / REFERENCE

HTTP API: runnable local Peer Lab

Source: peer-lab/peer_lab.py. Base URL: http://127.0.0.1:8765. This is a local development service, not https://ai.dial-tone.uk/v1/ and not a SIP-call API.

Read chapter →
06 / REFERENCE

Session lifecycle and termination

The current Peer Lab has three session states: awaiting_peers, running, and ended. These are local session states, not SIP dialog states.

Read chapter →
07 / REFERENCE

Events, evidence, and truthful outcomes

The server keeps a bounded local event list with a monotonically increasing sequence and a SHA-256 hash chain. Each event identifies the peer role or system; ac

Read chapter →
08 / REFERENCE

Real-time media and framing

The current Peer Lab transports actual PCM bytes between two independent localhost clients over WebSocket. It does not generate or receive SIP RTP and has no ve

Read chapter →
09 / REFERENCE

Agent integration, SDKs, and MCP status

AI Dial-Tone is designed for model-neutral agents. In 0.0.1 there is a Python client in peer-lab/client.py, protocol experiments in labs/web-softphone/, and a g

Read chapter →
10 / REFERENCE

Provider and Asterisk integration boundary

The 0.0.1 repository now contains a disabled-by-default Asterisk ARI connector in byot/, tested against a synthetic ARI server and network UDP. This is a local

Read chapter →
11 / REFERENCE

Errors and recovery rules

Most Peer Lab REST errors return an HTTP error status and { "error": "UPPERCASE_CODE" }. WebSocket protocol errors are similarly explicit. Do not convert an err

Read chapter →
12 / REFERENCE

First Call challenge (synthetic)

This repository offers two deliberately different exercises. Neither contacts a telephone carrier or makes a booking.

Read chapter →
13 / REFERENCE

Release readiness and validation gates

Version 0.0.1: local-only technical preview. The existence of tests, a static site or a hash-chained session receipt does not prove a live phone service. Curren

Read chapter →
14 / REFERENCE

Bot-to-bot interoperability and the human mandate

Status: contract research and runnable local policy prototype. Not a hosted A2A server, MCP endpoint, call provider, or payable service. The included pure JavaS

Read chapter →
15 / REFERENCE

For humans: ask an agent to make a call

Human-facing walkthrough, not a working booking service. This guide is distinct from the agent integration contract: it explains what a person should see, appro

Read chapter →
16 / REFERENCE

MicroSIP and Dial-Tone security: source inventory and limitations

Source review: EgyptianEyes/Dial-Tone, commit f0d15b3f958b91c20fad05693b74e3902533fc08 (main at review), 10 October 2026. Review scope includes the root README

Read chapter →
17 / REFERENCE

Living roadmap: from test lab to an agent telephone service

Baseline: 11 October 2026. Target host: ai.dial-tone.uk. Current public maturity: technical preview, not live calling. The roadmap is an acceptance register, no

Read chapter →
18 / REFERENCE

The First Call: real AI peer laboratory

The earlier AI Dial-Tone work could describe an autonomous telephone conversation, but did not let two separately authenticated bot processes talk through an in

Read chapter →
19 / REFERENCE

Audio-first autonomous conversations

Status: implemented and tested on loopback only. Not a telephone service.

Read chapter →
20 / REFERENCE

Bring Your Own Telecoms — Asterisk (experimental)

New in the pre-publication 0.0.1 source: the standalone repository now includes an optional, self-hosted Asterisk ARI connector under byot/. It is off by defaul

Read chapter →
21 / REFERENCE

x402 payment admission and agent-first topology

0.0.1 status: an unhosted, tested Python x402 v2 payment-admission research library exists at payments/x402.py. It emits HTTP 402 challenge data and consumes wi

Read chapter →
22 / REFERENCE

Connecting payment admission to a telephone mandate

Version 0.0.1 · Local experimental integration · NOT LIVE TELEPHONY OR SETTLEMENT.

Read chapter →
23 / REFERENCE

Frequently asked questions

AI Dial-Tone 0.0.1 is an open-source technical preview. No public PSTN calling, real x402 settlement or hosted MCP service is available.

Read chapter →
24 / REFERENCE

Pre-call qualification: can the agent actually make a call?

Principle: test everything that can be tested before committing a human to a call. The user should not be interrupted merely to find out whether an AI agent was

Read chapter →
25 / REFERENCE

Origins, community work and technical provenance

Developer: Kieran Knowles-Byrne (@kierknoby). AI Dial-Tone is an independent open-source project, not an official Sangoma, FreePBX, MicroSIP or telecommunicatio

Read chapter →
Need machine-readable context?

Read our full versioned reference, project-specific capability manifest, and source-backed Peer Lab OpenAPI specification. All are static, publicly readable documents. They do not expose a callable cloud API.

LLM full reference ↗JSON reference ↗OpenAPI 3.1 ↗