Worth noting the "Unix-inspired" framing is the HN title, not the README — the project itself pitches "minimalistic" and "optimized for memory footprint." Curious what the author means by Unix-inspired specifically, since a single-binary TUI running a multi-tool agent loop doesn't immediately read as do-one-thing-well-and-compose.

Working on a few things:

Rundash (rundash.ai) - an easy way to create automated AI agents that can run tasks for you with over 1000+ integrations. Built this from my own needs to run better meetings, discover product insights etc..

Provision (provision.ai) - how I run a team of openclaw agents without burning money on Mac minis. Each agent is given a dedicated email inbox (powered by Mailboxkit) and a dedicated chrome browser that you can connect via browser to unblock if needed. Currently doing some pilots with a few startups. It's interesting to learn how teams want to use AI agents like OpenClaw.

[unnamed project] - a macOS menu-bar AI agent that drives your real apps similar to Perplexity Computer. Hit ⌘⌘, type a task (optionally @-mentioning apps like @slack), and an agent Claude Code or Codex; clicks, types, scrolls, switches apps, and reads the screen via accessibility APIs, with a visible cursor so you can watch it work. Everything runs locally on your own logged-in Mac (BYOK to Anthropic/OpenAI), so there’s no cloud VM or re-auth flow. It also snapshots the frontmost app for ambient context ("summarize this page" just works) and supports parallel tasks with persistent history/workspaces. Pre-release, but the core bet is that desktop agents should feel like a teammate living in your menu bar, not a browser tab or rented remote computer.

Very interesting product. How is this compared to https://save.day?

I built https://storypanda.ai a while back to help with storytime with my daugther.. check it out, happy to take feedback.

Interesting, something similar to what I have in mind.

I did take break in those hours. Honestly it was tough to survive on 4 hours of sleep during weekdays. I usually slept in a bit on Sundays.

I would also recommend not to do it this way. It was brutal.

It's tough but feels worth it - I never feel like I've missed out on anything with my daughter since I'm always around. I think if I can just structure my day better it'll all work out a lot better, just haven't figured out how yet!

Awesome. I built StoryPanda[1] to do something similar. My daughter, and kids of my friends absolutely love creating a story every night.

1. https://storypanda.ai

Hey Obaid, I built something similar, https://storybird.ai/. Want to chat?

Me too: https://storykoala.ai/

Your https://storynoworky.ai unfortunately :(

I just wanted to continue the pattern in the thread :D

This looks great! What is the text-to-image model that you have used?

This is pretty neat. I am going to use it to monitor myself during the calls. I am curious about the tech behind this. Speaker identification locally on the machine seems like what's happening here. The nerd in me wants more tech deep dive :)

Let me know how it goes – Would love to hear your experience.

It's a small but solid ML model that I've been working on. And I've got a 'headphones'-free feature on my personal roadmap, too!

I have been looking into this lately as well. My problem is that even if I visit back those pages, I don't remember the context of why I bookmarked it.

I have been toying with a chrome extension that enables me to add "annotations" to these pages and it helps me find websites based on my note search. It's far from perfect but I realized that I remember my notes / thoughts more than the website url or name.

https://histre.com/ lets you add notes and highlights to your bookmarks, if that's what you're looking for. Disclosure: I'm working on it.

Neat. I will check it out!

In Firefox I heavily used tags, "tags are great, mini notes, super useful", but they're missing from Brave, Chrome, etc.

This is awesome (in a crazy way). I was playing with Resemble.ai [1] yesterday and was surprised by how good it was in replicating my voice with just a few minutes of dataset. This technology is going to keep on getting better by the minute.

As with any piece of technology, there are always good and bad actors.

1- [Resemble.ai](http://resemble.ai)

Botmock | Ottawa (preferably Canadian) or Remote | Full-Time | Frontend

Botmock is a collaborative design, prototype and testing platform for conversational experiences. We're a funded high-growth startup that's rapidly becoming the starting point for all conversational projects.

Our product is used by thousands of users to design, prototype and test conversational experiences for Amazon Alexa, Google Assistant, Facebook Messenger, Custom Website, SMS, Apple Business Chat and more.

We’re a remote-first team that thrives on flexibility and creativeness. Each team member gets perks like allowance for co-working space, equipment and all of the other benefits to help you make the most of your day.

We're hiring for one role, either remote or in Ottawa. Please note that we cannot sponsor visas at this time.

Description:

As part of our frontend team you will be working on building the core of Botmock. Our users spend on average 5-7 hours every day using our product. Our front-end stack is React, Redux with Rest API. We are looking for someone to help us take our front-end to the next level while working with the existing team.

Interview process: Call 1: We get to know each other. Call 2: We solve a technical problem together (max 40 mins) and ask questions (20 mins) Call 3: We either make an offer or give you feedback on why you weren't selected

If interested, reach out directly to me: obaid@botmock.com