Moss (YC F25)

Most websites have a lead capture problem. Visitors have questions. No one is there to answer them. Founding Agent is a voice AI agent that answers questions, qualifies prospects, and books meetings 24/7. Get early access → moss.dev/foundingagent

Excited to sponsor the YC x Medplum Hackathon organized by @Medplum1 Please join us on Saturday, Aug 1 @ YC

10,000,000 production conversation session minutes on @usemoss Last week we posted about hitting 5M. The week before that, 2M. The week before that, 1M. 1M took months. 1M to 10M took three weeks.

We hosted the Conversational AI Hackathon at @ycombinator last month. 450+ builders applied. Here's what 24 hours of building looked like. youtu.be/59W5eq02iRU

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.

We're live in 48 hours. Join us on Thursday, July 9 to see why Voice AI agents are replacing static websites, and watch us deploy one live. If you can't make it live, register anyway and we'll send you the recording. Register: luma.com/foundingagent

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 🧵

Check it out at github.com/usemoss/moss/t…

on-device AI is having its moment. Apple Silicon proved local inference works. retrieval is the next frontier. Moss 𝗦𝘄𝗶𝗳𝘁 𝗦𝗗𝗞 ships that. sub-10ms semantic search, fully on-device for iOS. no server, no round trips, no latency tax on every query. ↳ embed + query locally  ↳ push/pull cloud sync when needed  ↳ iOS 15+, one SPM line the same runtime powering 1M+ minutes of voice AI. now in your Xcode project.

Last week we crossed 1M real-time voice minutes on @usemoss. This week we hit 2M. I had to re-read the dashboard three times. The growth is accelerating faster than we expected. Here's what's happening. Teams that started with small pilots are going live in production. Countries we've never even marketed to are showing up in our logs. Engineers are integrating Moss on a Friday and their entire team is running it in production by Monday. The thing about infrastructure is that usage doesn't grow linearly. It stays flat while teams evaluate. Then one day, something flips. Production traffic turns on and the curve goes vertical. That's what's happening right now. And the wildest part? Most of these teams found us the same way. One developer tried it, it worked, they told another developer. We're just getting started.

Get started with our docs at - docs.moss.dev

we built Moss because voice AI pipelines were dying on retrieval latency. fixed that. now shipping it to your terminal. > 𝗽𝗶𝗽 𝗶𝗻𝘀𝘁𝗮𝗹𝗹 𝗺𝗼𝘀𝘀-𝗰𝗹𝗶 > 𝗺𝗼𝘀𝘀 𝗾𝘂𝗲𝗿𝘆 𝗺𝘆-𝗶𝗻𝗱𝗲𝘅 "𝘄𝗵𝗮𝘁 𝗶𝘀 𝗱𝗲𝗲𝗽 𝗹𝗲𝗮𝗿𝗻𝗶𝗻𝗴" sub-10ms. on-device. no infra. 1M+ minutes of conversations already running on Moss in production. the retrieval problem is solved.

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👇🏽 youtu.be/neXXdD1P8Bk?is…

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 👇

Attended the conversational AI hackathon by @usemoss at @ycombinator last weekend — built a voice agent that compares health insurance plans over a phone call. Good fun, great people! Love the vibe of SF ♥️

Come build agents that can finally hold a fluid conversation at the 24-Hour Conversational AI Hackathon, hosted by @usemoss at the YC Office, June 6-7. First place wins an interview with a YC partner: events.ycombinator.com/conversational…

Star the repo and try it out: github.com/usemoss/moss

𝟭𝟬𝟬𝘁𝗵 𝗣𝗥 𝗺𝗲𝗿𝗴𝗲𝗱 𝗶𝗻 𝘁𝗵𝗲 𝗠𝗼𝘀𝘀 𝗿𝗲𝗽𝗼. What started as an idea is now being shaped by a growing community. Every bug fix, feature, and improvement brought us here. Thank you to everyone who opened a PR, filed an issue, or left a review. You're building this with us. The best is ahead. #OpenSource #Moss #SemanticSearch #DevTools

Explore the open source repo and leave us a ⭐️ to support: github.com/usemoss/moss

𝗠𝗼𝘀𝘀 𝗰𝗿𝗼𝘀𝘀𝗲𝗱 𝟭𝟬𝟬𝗞+ 𝗽𝗮𝗰𝗸𝗮𝗴𝗲 𝗱𝗼𝘄𝗻𝗹𝗼𝗮𝗱𝘀. One bet: make semantic search fast enough that conversations flow at the speed of thought. Your conversational AI agent deserves sub-10 ms retrieval. With teams shipping Moss in production, our product did the talking. #SemanticSearch #AIAgents #VoiceAI