Build Your Own 100% Local AI Second Brain

2026-07-08 · Source: Daily Dose of Data Science · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, medium

Summary

Rowboat is an open-source, 100% local AI "second brain" desktop application available for Mac, Windows, and Linux, designed to manage dynamic work context. Unlike traditional wikis that compile static concepts, Rowboat builds a knowledge graph by ingesting conversations from sources like Gmail, Granola, and Fireflies. It extracts evolving entities such as decisions, commitments, and deadlines, storing them as plain Markdown files in an Obsidian-compatible vault located at `~/.rowboat/`. Users can integrate their own LLMs from Ollama, LM Studio, or hosted APIs by configuring `~/.rowboat/config/models.json`, and connect Google Cloud OAuth credentials for direct API calls to Gmail, Calendar, and Drive. This system enables context-aware queries, such as preparing for meetings or generating daily voice summaries, by dynamically traversing the graph and automatically updating "live notes" as new information arrives.

Key takeaway

For AI Engineers or MLOps teams seeking a robust, local, and open-source solution for personal knowledge management, Rowboat offers a compelling framework. By leveraging its dynamic knowledge graph over a static wiki, you can ensure your AI assistant remains current with evolving project details, decisions, and commitments. Consider integrating Rowboat to maintain an always-up-to-date "second brain" that directly queries your communication channels and LLMs without proprietary lock-in, enhancing contextual awareness for daily tasks.

Key insights

Rowboat transforms static wikis into dynamic knowledge graphs for evolving work contexts.

Principles

• Knowledge graphs track state across conversations, not just compiled concepts.
• Entity files are created only with sufficient evidence to prevent graph pollution.
• Query cost remains flat as the graph grows by loading only relevant entities.

Method

Install Rowboat, configure your LLM in `models.json`, set up Google Cloud OAuth for data sources, optionally add Fireflies/Granola API keys, then query the graph.

In practice

• Prepare for meetings by querying "Prep me for my 2pm meeting with Sarah Chen".
• Get a voice summary of your day using "Create a voice summary of my day ahead".
• Tag any note with "@ rowboat" for automatic, continuous updates.

Topics

• Rowboat
• Knowledge Graph
• Local AI
• Obsidian
• LLM Integration
• Personal Productivity
• Context Management

Code references

• rowboatlabs/rowboat

Best for: AI Engineer, Software Engineer, MLOps Engineer

Related on AIssential

• Your Personal AI Assistant That Never Forgets — An AI-powered second brain integrates a wiki, CRM, and journaling for active knowledge processing and retrieval.
• rowboatlabs / rowboat — Rowboat is a local-first AI coworker building a long-lived, editable knowledge graph from user data.
• Forget Prompt Engineering: Why Your Knowledge Graph is the Only AI Moat That Matters — A proprietary knowledge graph, not AI models, forms the only durable competitive advantage in the AI era.
• PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents — PAI-2 enhances LLM factual correctness and reduces hallucinations via dynamic knowledge graph traversal and planning.
• Engineering managers ditch cloud AI for local LLMs — Local LLMs now offer a credible, cost-effective alternative for many enterprise coding tasks, breaking the cloud-only binary.
• Give Your AI Unlimited Updated Context — An LLM-maintained personal wiki creates a persistent, compounding knowledge artifact, eliminating repetitive context setup.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Daily Dose of Data Science.