Hey PH I'm a solo maker, and this is the product I wish existed two years ago.
I was great at starting things and terrible at finishing them. So I built Pactio a weekly accountability pact. You pick a direction (start a habit, or stop one), sign a 30-day pact, and a real person reviews your week with you. No AI coach pretending to care someone actually asks how it went.
It's live now and I'd genuinely love feedback from this community.
First month is $1 with code PACT1 if you want to poke around: https://mypactio.com
Hey, I'm Gordana, part of the team behind Cluing, and today Hosted Agents are live - collaborative agents that build, learn, and publish in one place.
Btw, I'm equal parts excited and terrified typing this.
We built agents for ourselves first but since we got so much value out of it, keeping it internal started to feel wrong. So today, it becomes part of the product for everyone:
Hosted agents that ship - describe a task, an agent builds and publishes it live, on your own domain. No setup, no terminal, no laptop babysitting.
Native memory - agents run on your knowledge and context, so no re-explaining every time.
Dynamic skills - reusable playbooks powered by your knowledge, not static files. Update the Topic, the skill updates itself.
Connectors with encrypted secrets - your agents plug into your tools securely.
Real collaboration - your whole team and your AI work from the same brain.
Your agent changed a shared helper. The edit looks tidy. Which other parts of the project need a closer look?
I m Kevin, the maker of Brain Scanner. Here is a concrete review exercise you can use with your next agent-assisted change:
1. Pick one changed helper or module. Write down the behavior you expect to remain the same.
2. Inspect its recorded relationships in the project graph. Use those connections to identify files and symbols worth reviewing, then check the current source for callers and indirect uses.
Three weeks ago I handed in my notice at a six-figure job. No co-founder, no funding, no safety net beyond 4 months of savings. I did it to build one small SaaS product.
Since then I've had the same thought roughly every second day at 2am: this is the dumbest possible moment in history to do this.
Here's the fear, stated plainly, because I'd rather hear it argued with than keep circling it alone:
1. Every SaaS is now one feature announcement away from irrelevance. I don't mean "a competitor might launch." I mean an AI lab ships a model update, a checkbox appears in a product 400 million people already pay for, and my entire reason to exist becomes a bullet point in someone else's changelog. I didn't build something a big company could copy I built something a big company could copy by accident, on a Tuesday, while shipping something else.
I made Agent Diff Sentinel, a small CLI that scans a git diff before merge and flags things worth checking first: auth/billing/security changes, secret-looking lines, missing tests, dependency drift, oversized diffs, and temporary markers.
Repo: https://github.com/subhanA-UA/ag...
Live page: https://subhana-ua.github.io/age...
Curious how other builders review AI-assisted PRs right now.
I ve been thinking about something that doesn t get enough attention in the gaming world:
Accessibility isn t only about making a game playable. It s also about making the gaming community accessible.
A blind gamer might find an accessible game, but what happens when they want to meet other players, talk about games, make friends, join a community, or simply hang out?
That question is what led us to build Dora Station.
