Praxos – team messaging with built-in memory
Hey HN! What does a regular workflow at a startup look like? Probably like this: > One founder talks to customers > Another founder builds > A customer asks for something. The first founder explains it to the second. The second founder explains it to Claude > Two weeks any one of the founders asks one of the following questions: \* Why are we building it this way? \* What happened here? \* What did we promise ACME we’d do? \* How far along are we on X? > Then you scream on the inside because you have to figure out what happened... Before agents, the person who did one part of the work…
What it does
Messaging for people and AI agents working together.
In the maker’s words, at launch
Hey HN! What does a regular workflow at a startup look like? Probably like this: > One founder talks to customers > Another founder builds > A customer asks for something. The first founder explains it to the second. The second founder explains it to Claude > Two weeks any one of the founders asks one of the following questions: \* Why are we building it this way? \* What happened here? \* What did we promise ACME we’d do? \* How far along are we on X? > Then you scream on the inside because you have to figure out what happened... Before agents, the person who did one part of the work usually held a mental map. They could share the context with other people. Increasingly, they can’t. Small teams can run far more work in parallel than ever before thanks to AI, but someone now has to connect all that context manually. The reasoning behind one product change might now be scattered across a customer call, two emails, a Slack thread, and four Claude conversations. Praxos is a team messaging app. It has channels, groups and threads like you’d expect. However, places where work happens—Github, harnesses, email, calls—get linked and converted into a living record of your company. This means everyone is always up to date with the latest developments. Agents can join conversations and inherit the same context humans do. Here are examples we’ve seen in production: You talk to a customer. Later, when an engineer or coding agent works on the feature, your conversation and the customer’s information are already in context. A new engineer picks up an existing project. They have immediate access to info about who worked on what part of the code base, the deltas across changes, and a granular view of their conversations with coding agents. There’s no need to interrogate the CTO. Three weeks later, someone asks why the engineer made a certain decision about the feature. Praxos fetches the engineer’s convos, the original feature request and call logs between the founder and the engineer. Then it contextualizes the work. We’re early, but the core product already works and is in use. You get messaging, search, memory and connectors. You can bring your own agents, use ours, or both. A desktop app is going live next week. We’re building native calls and mobile apps, so that all the communications that go into a company’s history can happen on Praxos. If you’re a 2 to 10 person team where one person is spending all day with customers while the rest of the team is shipping with Claude/Codex, we’d love to personally onboard you. Especially if you’ve already caught yourself asking “what did the customer want?” or “what’s going on with X?” last week. The first 10 teams to sign up get Praxos for free for 6 months. Email [email protected] to get started!
Does the same job
all alternatives →
- OSOne-Stop inbox for customer communication.2011 · ▲13
You use Twitter, Facebook as well as email to communicate with your customers? With all these different services, it has become very hard to manage and keep track of all the conversations happening. My co-founder and I noticed this some months ago and asked people how they would like to handle this. And so we have come up with a new solution. We launched into public beta about two weeks ago. The problem was: We had a very hard time explaining to people how we help them and why that's relevant. We were too technical and nobody really understood exactly what it was that we did. So we took a…
- CACoding Agents swarming your codebaseSep 2025 · infrastructureas.ai · ▲9
I built this because I was tired of creating pull requests in 20 repositories just to change a single line of workflow job version. With Infra as AI, just mention the change. Agents work on all repos in parallel, read the docs, make a bunch of PRs and fill in the description. You can see the demo of the actual dashboard in the landing. Let me know your thoughts :) It means a lot to me!
More work this month
the category →
The app store for voice native apps that lives in your notch
Work · 28d ago · voiceos.com
The New Calendly▲211Handle all of the work before, during, and after meetings
Work · 17d ago · calendly.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com