5,000,000 production voice minutes on @usemoss
Not sandbox traffic. Not internal QA. Real production minutes from teams running voice agents with paying customers on the line.
Three weeks ago we were at 1M. Last week, 2M. Today, 5M.
Here's what 5M minutes actually looks like under the hood:
→ Millions of retrieval calls resolved in under 10ms
→ Customers jumping from 300K minutes/month to 100K minutes/day overnight
→ Identical latency at 1x, 10x, and 50x load
→ Zero retrieval failures across every traffic spike
The teams building on Moss are powering voice agents for global enterprises across 100+ countries. When their customers' customers are on the line, a slow retrieval or a missed lookup isn't a bug. It's a broken experience.
We built Moss to be the kind of infrastructure you stop thinking about. It just works. Every scale. Every spike. Every time.
We're just getting started.
We just merged our 100th pull request in the @usemoss repo.
That number stuck with me. Not because it's big. Because of who's behind it.
We're a 10-person team. We don't have a DevRel department. We don't have a community manager. We have engineers who ship during the day and review community PRs at night.
And somehow, contributors keep showing up.
Someone added a Haystack integration. Someone built a voice agent demo and put it in our community-demos folder. Someone opened an issue at 2am about an edge case we missed and had a fix ready by morning.
18 framework integrations. Working examples across Python, TypeScript, C, Go. Voice agent templates. A cookbook folder that grows every week.
None of that was on a roadmap. Developers built what they needed and contributed it back.
The repo tells the real story of how Moss is being built. Not in a boardroom. Not in a marketing doc. In pull requests, from people who actually use it.
100 PRs in. The repo is open. The roadmap is public. And we're just getting started.
A friend had a nightmare experience calling Tesla insurance last week. Their voice AI experience was so bad he spent every trick to get to a human agent. He said "they should use Moss." I told him the business incentives may not actually be aligned.
Here's what I mean 🧵
We launched Founding Agent earlier this week and didn't expect this kind of response. One of the teams from our hackathon just sent me this video. Had to share👇🏽
https://t.co/eRJYdM2XAH
the ux of the world is changing.
every generation of computing since the 60s has stripped away a layer of friction. each shift let more people do more, with less syntax to learn.
command line (60s): type the exact syntax.
mouse + GUI (1984): see it, click it.
touch (2007): just tap.
and now, since GPT, an entire generation has been trained to ask.
conversation is the default interface now.
so we built for what comes next: the agentic web.
voice ai for websites → https://t.co/f4KlTlNVmh
we're just getting started.
Today we're launching Founding Agent.
For 25 years, a website's answer to "I have a question" has been a search box and a contact form that goes nowhere. So visitors leave - and you never know they were there.
Founding Agent is a voice AI agent that lives on your site and actually talks to people. It answers their real questions instantly, qualifies who's a fit, and books the meeting while they still care.
It feels like a real conversation because retrieval runs in under 10ms. No lag, no "thinking" dots. It's built on the same infra 1500+ developers are already using at @usemoss
Websites have been one-way mirrors for too long. Time they answered back.
Early access 👇