workflowstacks
voice-ai

Patter: Own Your Voice AI Stack

Give your AI agent a phone number with Patter, an open-source voice-AI SDK for founders, with support for Python and TypeScript.
1,018 stars104 forksPythonHealth Score 9/10Updated 7/15/2026100% free · open source
What it does

Patter gives your AI agent a phone number, allowing users to interact with your AI via voice calls using a simple, open-source voice-AI SDK

Install / run
pip install patter
When to use it
  • You want to build a conversational AI interface that users can interact with over the phone
  • You need a lightweight, customizable voice-AI solution that integrates with your existing tech stack
  • You prefer to own and control the underlying infrastructure and data for your AI-powered voice applications
Quick start
  1. 1Create a new Patter project by running `patter init`
  2. 2Configure your Patter project to use a supported telecom provider like Twilio, Telnyx, or Plivo by editing the `config.json` file
  3. 3Define your AI agent's voice interaction logic using Python or TypeScript, referencing the Patter SDK documentation for available APIs and examples
  4. 4Start your Patter server and make it accessible to users by running `patter start`
  5. 5Test your Patter-powered voice AI application by calling the assigned phone number and interacting with your AI agent
Ready-to-paste prompt
Create a simple voice-powered FAQs system by defining a Patter intent like `FAQ_INTENT = patter.Intent('faq', ['What is Patter?', 'How do I use Patter?'])`
Heads up: You need to sign up for an account with a supported telecom provider like Twilio, Telnyx, or Plivo and obtain the necessary API credentials to configure Patter
Saves to your device

Topics

ai-agent
ai-phone-agent
hermes-agent
llm
mastra
open-source
openai
openclaw
python
realtime-api
sdk
speech-to-text
telnyx
text-to-speech
twilio
typescript
vapi-alternative
voice-agent
voice-ai
voicebot
How Patter: Own Your Voice AI Stack works
Codeflow
Free to inspect

Patter: Own Your Voice AI Stack is a very large Python project (~117k lines across 429 code files, plus 361 test files). Setup is light: installs like a normal app — add your API keys. Reading the code is optional. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~117k lines · 429 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app — add your API keys. Reading the code is optional.
Runs on
Docker
Needs API keys (.env)
Python 50%TypeScript 44%HTML 5%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    create-getpatter/index.js
    Where the program starts running
  4. 4
    .env.example
    The API keys and settings you must provide
  5. 5
    examples/hermes-phone-agent/.env.example
    A worked example — copy this to get going
What's in each folder
docs/Documentation158 files
examples/Examples you can copy21 files
libraries/python/Folder393 files
libraries/typescript/Folder358 files
dashboard-app/Folder33 files
create-getpatter/Folder4 files
scripts/Helper scripts2 files
tests/Tests — proof it works15 files
READMEHas testsDocumentedCI checksDocker readyExamples includedMIT licenseUpdated this month
Quick Actions
Details
Creator
PatterAI
Language
Python
Category
voice-ai
Published
4/7/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.