Overnight Brain: A Lazy AI Assistant That Works the Night Shift

Description and use

A local, open‑weight AI assistant that processes queued tasks overnight and delivers a morning digest, reducing daytime cognitive load.

Problem

Need to defer non‑urgent AI tasks to overnight so the user can sleep without waiting for answers or carrying a mental to‑do list.

Outcome

The system saves the user from waiting for answers and reduces mental load, enabling a morning digest of completed tasks.

Workflow

• 1. Add tasks to the queue via the web app during the day.
• 2. At 1 a.m., the worker script wakes and sends each queued task to Gemma via Ollama.
• 3. Gemma generates an answer and a short good‑morning note.
• 4. The worker saves the answer to SQLite and updates the digest.
• 5. In the morning, the user reads the digest in the app.

Evidence

Overnight Brain is a lazy person's AI assistant. During the day, I drop things into a queue: questions I've been meaning to look into, long articles to summarize, big goals to break into steps, and messages I keep putting off. At night, Google's open-weight Gemma model runs right on my laptop and works through the list one task at a time while I sleep.

Source

I queued three tasks at 10 p.m., went to bed, and at 1 a.m. my laptop started working through them on its own.

Source

At 1 a.m., the worker sends each task to Gemma through Ollama on my own laptop, saves the answer, and then has Gemma write the short good‑morning note at the top of the digest.

Source

No cloud AI services are involved.

Source

The 8 GB plot twist: My first model download was 9.5 GB. Then I checked my MacBook and found it only has 8 GB of memory, so the model would never fit. I switched to a smaller, compressed version of Gemma that's built for lighter machines, and it ran fine at about a minute per task.

Source