I Built SlothFlow AI: A Local-First AI Assistant That Turns Brain Dumps Into Action Plans 🦥

Description and use

SlothFlow AI turns unstructured brain dumps into actionable tasks using a local LLM or rule‑based fallback, stores them locally, and provides a workflow for review, tracking, and daily reset.

Problem

Users struggle to decide where to start when overwhelmed with tasks and brain dumps.

Outcome

SlothFlow AI reduces manual organization effort by converting brain dumps into structured task plans locally, enabling users to focus on execution rather than planning.

Workflow

• 1. User writes a brain dump in plain language.
• 2. SlothFlow AI processes the input using a local LLM (Ollama) or a rules‑based fallback.
• 3. AI outputs a draft task list with priorities and time estimates.
• 4. User reviews and saves selected tasks to the workspace.
• 5. Tasks are tracked, completed, or deleted in the local SQLite database.
• 6. Daily Reset view summarizes unfinished work and estimated time.
• 7. User can add new tasks manually or adjust existing ones.

Evidence

I wanted to build something that could help with that problem, so for the Hacktoberfest DEV Challenge Week 3, I built SlothFlow AI — a local-first productivity assistant designed to turn overwhelming brain dumps into manageable action plans.

Source

When a compatible local model is available, SlothFlow uses it to generate a more contextual task plan. If Ollama isn't available, a built-in rules-based fallback can still produce a basic checklist.

Source

The project uses a lightweight stack: Python — application logic, FastAPI — REST API and backend, Ollama — optional local LLM inference, SQLite — local task persistence, HTML, CSS and JavaScript — responsive frontend, Pytest — automated testing.

Source