micro

Go2025–2026

micro / mu

mu

An open runtime for personal assistants.

Languages & Compilers

Explore on GitHub Read Hacker News discussions

2Distinct people

14Mentions

0Explicit recommenders

439GitHub stars

REPOSITORY AT A GLANCE

What to know before exploring

What it is

An open runtime for personal assistants.

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 12:54:37 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by month14 dated mentions

Observed mentions: 2025-09-22 17:00:49 UTC to 2026-09-14 11:53:11 UTC.

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges

UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
Period	Start (UTC)	End (exclusive, UTC)	Mentions	Submissions	Comments
Sep 2025	2025-09-01 00:00:00 UTC	2025-10-01 00:00:00 UTC	1	0	1
Oct 2025	2025-10-01 00:00:00 UTC	2025-11-01 00:00:00 UTC	0	0	0
Nov 2025	2025-11-01 00:00:00 UTC	2025-12-01 00:00:00 UTC	2	1	1
Dec 2025	2025-12-01 00:00:00 UTC	2026-01-01 00:00:00 UTC	2	0	2
Jan 2026	2026-01-01 00:00:00 UTC	2026-02-01 00:00:00 UTC	0	0	0
Feb 2026	2026-02-01 00:00:00 UTC	2026-03-01 00:00:00 UTC	1	0	1
Mar 2026	2026-03-01 00:00:00 UTC	2026-04-01 00:00:00 UTC	2	2	0
Apr 2026	2026-04-01 00:00:00 UTC	2026-05-01 00:00:00 UTC	0	0	0
May 2026	2026-05-01 00:00:00 UTC	2026-06-01 00:00:00 UTC	0	0	0
Jun 2026	2026-06-01 00:00:00 UTC	2026-07-01 00:00:00 UTC	1	0	1
Jul 2026	2026-07-01 00:00:00 UTC	2026-08-01 00:00:00 UTC	1	1	0
Aug 2026	2026-08-01 00:00:00 UTC	2026-09-01 00:00:00 UTC	2	1	1
Sep 2026	2026-09-01 00:00:00 UTC	2026-10-01 00:00:00 UTC	2	0	2

What Hacker News says

14 sources

asim·Sep 14, 2026

Micro - a personal AI agent - https://micro.mu Still iterating. Started with something else, then turned that into tools, then turns that into agents, then turned that into an assistant. Now trying to make it generally useful, quite painful at times... but want something that is not Muse or ChatGPT or Claude or Gemini... and not Hermes or OpenClaw. Currently just fixing all the broken styling/css, etc, no separate frontend, single Go binary. Self host if you like - https://github.com/micro/mu

In Ask HN: What are you working on? (September 2026)

asim·Sep 9, 2026

Hello. Me again. I think for 10 plus years I've been trying to make something work. Like most of us engineers, we have a lot of ideas. And after spending a bit of time at Google in 2011-2013 I felt like I understood the direction of where things were going. Obviously technology takes time to catch up. I don't think personal assistants are the end point. To be honest, I think ambient computing and emergent behaviour is sort of a feature thing. But there are stepping stones. Personally having seen Muse and other things from large players. I feel like we have to keep attempting to build alternatives. I'm a big Google user. I'm a big Gmail user. Big, but at this point in the field of personal AI, I do think there's an opportunity to start to shift some of that dynamic. I've always built infrastructure from the ground up and so many of you wil

Read the rest

l have seen me here over the years building a go framework or building a platform as a service or apis for developers. Ultimately, it was all attempting to get at some sort of end consumer and personal solution. I just felt like it would be really great if I could run the whole stack myself. But I never felt like the tools were in the place for that. Now it really feels like not only can you do it but you don't have to assemble the parts. You can literally build it all in one. So one of the things I've done is actually baked in an SMTP server and an xmpp server and some other protocols. I can also send SMS and WhatsApp to this. I can email it. I can use an IMAP inbox if I really want to. And I can backup all my storage S3. I'm showing the front door but there's also a back door which is the apis and the MCP server. It's all open source https://github.com/micro/mu I've posted that here before. But you'll see from my history I think the goals keep changing or maybe not the goals but the way in which is presented. Ultimately, I think we should have an all-in-one solution that you can run yourself, but also that we have some alternative to what's out there. I think I'm a really big fan of email and smtp and the open protocol allowing you to self-host if you want. But ultimately we all went to big providers but there's potential for standalone solutions and I think the same should be the case for not just personal AI assistants but all home assistant software. I think if you could run the full stack in the cloud or on a device in your house that would be the end game. At which point you could potentially cut the reliance on a lot of these large providers who have access to all of your data. I'm not saying I have all the answers today but this is just one way I'm presenting it.

In Micro – A Personal AI Assistant

asim·Aug 10, 2026

Mu - Tools for Agents. An MCP server and web app that provides real time access to news, markets, weather, video, places, search, etc. It's sort of extension of a previous idea I had to put all the key tools and services behind a single api and access token. I don't know that it's quite there yet. The idea might change. Still looking for feedback. https://micro.mu https://github.com/micro/mu Also have an agent harness and service framework in Go https://github.com/micro/go-micro

In Ask HN: What are you working on? (August 2026)

asim·Aug 2, 2026Submission

Show HN: Mu – Tools for Agents

52 points · Open discussion

asim·Jul 21, 2026Submission

Show HN: Mu – A Personal Home Server

1 points · Open discussion

asim·Jun 8, 2026

Originally I felt there should be an alternative to Google and Facebook. It felt like our lives were being ruled by tech giants even ten years ago..and then all the advertising and algorithms really messed with us. I personally wanted an alternative way to use the web. So it's based around what I'd use on a daily basis. And then the idea of being able to extend it with a native app builder. The big stuff I continue to build with Go but ad-hoc things I can knock out with some JS in the app itself. Its open source (https://github.com/micro/mu).

In Ask HN: What are tools you have made for yourself since the advent of AI?

asim·Mar 26, 2026Submission

Show HN: Micro – apps without ads, algorithms or tracking

For over 10 years I've been trying to accomplish something that took Claude Code and a lot of failure to realise. We need alternatives to big tech and we're not working hard enough to make that happen. In an era of addiction, usury and exploitation it's now time we seriously consider alternatives. Proton and the like worked on privacy focused individual services at a pain stakingly slow pace. Maybe for good reason. But it was also in an era pre AI. 10 years ago I was convinced the super app model would work. And that a platform needed to exist to facilitate that. Today I realised the tech doesn't matter, the idea and execution from the top down does. I put aside my technical perfectionism to try pull together a solution to some of the problems that plagued my own life with tech addiction and I rewrote and threw away this thing multiple ti

Read the rest

mes over the years pre AI and after. I burned VC funding, I burned bridges, I burned community trust in an open source project. But it was all in the pursuit of something I was compelled needed to exist. I use this on a daily basis probably 10+ times a day. Every person has different use cases but for me what's key is to try pull all the digital daily habits in one place and then be able to build on that. I can't replace my own google usage for mail yet but I also saw a need for something in between by private email and a work email. There's so much more I could say but essentially Micro and the app Mu (https://mu.xyz) is the culmination of many years of work. And it's also open source. https://github.com/micro/mu. Please provide feedback. Please tear it apart. Please poke holes in my theory. I'm not looking for hype. I really do just think we need an alternative to big tech.

6 points · Open discussion

asim·Mar 2, 2026Submission

Mu v0.11.0

2 points · Open discussion

asim·Feb 23, 2026

We got here iteratively..not all at once. So the path back...it's iterative. I shouldn't even say back. We're not going back. We have to go in a new direction. And again it's evolutionary. So ultimately a lot of these big systems and big tech companies aren't going anywhere and they will be integral to all infrastructure for the foreseeable future whether that be technical, financial or related to public services. But as individuals we can slowly shift some of our efforts elsewhere in ways that it might matter. Here's my small contribution to that. https://github.com/micro/mu - an app platform without ads, algorithms or tracking.

In A simple web we own

asim·Dec 15, 2025

Mu - a personal app platform that includes chat with AI, news, video, posts and now mail. Solving a personal problem with ads, algorithms, tracking. Tech is too addictive now. We need to get back to utility value. I'm trying to build an alternative with myself as user 1. https://mu.xyz https://github.com/asim/mu

In Ask HN: What Are You Working On? (December 2025)

asim·Dec 11, 2025

A little while ago I posted Mu on here asking for feedback. It was really useful. I was hoping I could get a bit more feedback as I iterate on the product. Mu is a personal app platform that provides services without ads, algorithms, or tracking. Source: https://github.com/asim/mu Originally I wrote it entirely for me. There are still aspects that need adapting to be more broadly adopted but I'm working on it e.g card customisation on home screen.

In Ask HN: Can I get feedback on this product

bArray·Nov 29, 2025

> Big tech failed us. Uses Go, a language written by and maintained by Google [1]. Uses co-pilot written by GitHub for development [4]. Mu is £11 a month and you cannot see any screenshot of what you are getting [2], the same price you could buy a cheap VPS for [3]. The two authors of the project are asim and co-pilot. The commits have meaningless messages [4]. I would run a million miles away from this. [1] https://en.wikipedia.org/wiki/Go_(programming_language) [2] https://github.com/asim/mu [3] https://www.racknerd.com/BlackFriday/ [4] https://github.com/asim/mu/commits/main/

In Show HN: Mu – The Micro Network

asim·Nov 24, 2025Submission

Show HN: Mu – The Micro Network

65 points · Open discussion

asim·Sep 22, 2025

I don't think they actually know what the future business model is. No one really knows. What people are presenting is iterative models. That's fine but the model will be quite different. Ok we'll need subscriptions and to pay creators but I believe if everything is crypto and stablecoin based it's all going to be pay per view or pay per query because you know a lot of people just want that specific content from a specific source because of reputation or because that's what they like. I'm not paying for 5 different agents for that bespoke experience just like I'm not paying for NYT, WSJ and multiple other publications because it is insanity to price up what should effectively be pay per article. So maybe on the backend creators get a royalty kick back just like the music industry but on the consumer side I definitely think beyond subscrip

Read the rest

tions with the advent of crypto wallets we're going towards micro transactions for everything. Ok the the toxic nature of the internet and social media in general and what has become of our digital age, totally agree that it's rage and click bait. I wrote something to that effect here https://github.com/micro/mu/issues/27. But I personally don't think we're going to directly interact with agents the whole time. They will exist, they will be somewhere in the middle layers, there might even be a chat interface that replaces search queries with answers but I think the whole web as a whole and social media needs a rethink. Ads as a business model has to die, even though clearly it won't and we need to shift our attention elsewhere.

In A New Internet Business Model?