This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Patter connects your AI agent to a real phone number in 4 lines of Python or TypeScript. MIT-licensed. Pick your carrier (Twilio, Telnyx, Plivo) and voice stack, run it on your laptop, and see every call's cost and latency in a self-hosted dashboard. Python & TypeScript, MIT licensed, sub-500ms latency.
Hi Product Hunt! Francesco here! Nico and I are building Patter.
Last year I tried to put an AI agent on a real phone number and lost two weeks to plumbing: carrier websockets, mu-law resampling, barge-in, voicemail detection. None of it was the agent. All of it was glue.
Patter is that glue, open-sourced. MIT, Python + TypeScript, same API in both.
Don't take my word for it, call the demo: +1 (920) 7-PATTER (or +1 (920) 772-8376)
An agent built on the SDK picks up. It's rate-limited, so if it stops answering we hit the daily cap.
What you get:
-- Your carrier: Twilio, Telnyx, or Plivo — swap in one line
-- Three voice modes from one API: speech-to-speech realtime (OpenAI Realtime, ElevenLabs ConvAI), the pipeline (Deepgram STT → your LLM → ElevenLabs TTS), or hybrid — 27+ provider integrations across the stack
-- Barge-in, VAD, transfer, DTMF, voicemail drop, recording
-- Self-hosted dashboard: every call's transcript, latency, and cost — your data, your servers
-- Local dev with a built-in tunnel (tunnel=True) — test a real call from your laptop, no deploy
Honest framing: if you want something managed and working this week, Vapi and Retell are good at that. Patter is for when you want to own the stack — swap any layer, keep your data, see what every call actually costs.
Current release is 0.7.0, 4,500+ tests green across both SDKs, 950+ stars on GitHub.
github.com/PatterAI/Patter
If you need, plz ask me anything about telephony plumbing, latency budgets, or why barge-in took longer to tune than the rest of the pipeline combined
No comment highlights available yet. Please check back later!
About Patter on Product Hunt
“t-mobile for ai agents”
Patter was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #91 on the daily leaderboard. Patter connects your AI agent to a real phone number in 4 lines of Python or TypeScript. MIT-licensed. Pick your carrier (Twilio, Telnyx, Plivo) and voice stack, run it on your laptop, and see every call's cost and latency in a self-hosted dashboard. Python & TypeScript, MIT licensed, sub-500ms latency.
Patter was featured in GitHub (41.3k followers) on Product Hunt. Together, these topics include over 24.9k products, making this a competitive space to launch in.
Who hunted Patter?
Patter was hunted by francesco rosciano. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Patter stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
francesco rosciano