Imogen F. Jones

I keep seeing tools talk about how many agents they can run in parallel or how much of the backlog they can take on.

But every additional agent also creates more work to review, more decisions to make and more places where something can quietly go wrong.

https://www.producthunt.com/prod...
Meridian finished as the #1 Product of the Day on Product Hunt and crossed 400 downloads on its first day.

We built Meridian because meaningful work often disappears between debugging sessions, unexpected fixes, and updates written from memory. It is an open-source, MIT-licensed, local-first AI work journal that runs on your device, organizes your activity into a clear timeline, and drafts worklogs and project updates for you to review and approve.

Now we want to top the August monthly leaderboard, and we need your support. Please upvote Meridian on Product Hunt, download it, and star the GitHub repository.

If you want me to share Meridian s daily download numbers, comment below and I will post them.

We use AI to improve something in the process (mostly to speed up the process).

But whenever I see and suspect that something is generated by LLMs, I feel that the person on the other side has slopped it a bit (and subconsciously I perceive it as "something less").