Twagiramungu Yves

Closed-source software asks us to trust what we cannot inspect. We want to build differently.

Three months ago, my co-founder and I quit our jobs to build Meridian full-time. It is an open-source, local-first AI work journal that runs on your device, captures your development activity, and drafts clear worklogs and updates for tools like Jira. Nothing leaves your device until you approve it.

Meridian is MIT-licensed and free for individual developers.
Your thoughts and support would be really helpful

GitHub: https://github.com/Meridiona/mer...

The App Store shows downloads, revenue, crashes. Fine as a pulse check. Not enough if you care what people do inside the app: which paywall they hit, whether they finish a session, whether a feature even got used.

For Briskly I built a small event tracker and a private dashboard for that. It works. I m just not sure it s the smartest use of solo time, or if there s a simpler setup most people use.

Two hours into a refactor yesterday, my agent wrote a helper function the exact same one it wrote 90 minutes earlier in a file it created itself. Then it apologized. It always apologizes.

The easy diagnosis is "it ran out of context". Except my session was sitting at 120K in a 200K window. Nothing overflowed. The context didn't run out it rotted.

You have two budgets, not one:

• Hard Budget: Token limit. You notice it when the API errors out.

• Soft Budget: Attention quality. It drains silently long before you hit the limit.