rowboatlabs / rowboat

2026-02-13 · Source: Github Trending: All languages · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Novice, short

Summary

Rowboat is an open-source, local-first AI coworker application designed for Mac, Windows, and Linux that builds a long-lived knowledge graph from a user's digital workspace. It connects to email, meeting notes (via Granola, Fireflies), and voice memos to capture context, decisions, and commitments. This accumulated knowledge, stored as an Obsidian-compatible vault of plain Markdown notes, enables Rowboat to assist with tasks like generating PDF decks, preparing meeting briefs, drafting emails, and creating project updates. Users can visualize and edit their knowledge graph, and the system supports local models via Ollama or LM Studio, as well as hosted models with user-provided API keys. Rowboat also features background agents for automating routine tasks and integrates with external tools through the Model Context Protocol (MCP).

Key takeaway

For product managers or entrepreneurs seeking to enhance productivity and knowledge retention, Rowboat offers a compelling solution by centralizing your work context into an editable, local knowledge graph. This approach ensures your data privacy and allows for continuous learning, enabling you to generate documents, prepare for meetings, and automate routine tasks more efficiently. Consider downloading Rowboat to experience how a compounding memory system can streamline your daily operations and decision-making.

Key insights

Rowboat is a local-first AI coworker building a long-lived, editable knowledge graph from user data.

Principles

• Context accumulates over time.
• Relationships are explicit and inspectable.
• Data remains local and user-editable.

Method

Rowboat connects to communication channels, extracts context into an Obsidian-compatible Markdown knowledge graph, and uses this graph to generate artifacts and automate tasks.

In practice

• Generate PDF slides from existing context.
• Automate daily agenda voice notes.
• Integrate with external tools via MCP.

Topics

• Knowledge Graph
• AI Assistant
• Local-first AI
• Model Context Protocol
• Personal Knowledge Management

Code references

• rowboatlabs/rowboat

Best for: Product Manager, Entrepreneur, Software Engineer, AI Product Manager, Business Analyst

Related on AIssential

• Connecting the Dots with Context Graphs — Stephen Chin, Neo4j — Context graphs integrate LLMs with knowledge graphs to provide grounded, explainable, and auditable AI-driven decision-making by connecting disparate enterprise data.
• Distill, the Story of an ex-Colleague — AI agents can now automate knowledge extraction from departing employees, prompting counter-measures to protect individual contributions.
• The Business Engineer Agent — Scaling human thought involves rapid visual interaction and personalized AI agents that learn user identity.
• Local AI: How & Where To Start Building Something You Can Monetize — Local AI monetizes idle hardware by building workflow-based agents augmented with robust, structured knowledge and memory.
• Give Your AI Unlimited Updated Context — An LLM-maintained personal wiki creates a persistent, compounding knowledge artifact, eliminating repetitive context setup.
• Knowledge Graph Engineering For Agents: The Multidomain Problem — AI agents require explicit engineering to integrate multi-domain knowledge and accumulate persistent memory, unlike human pattern-matching.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Github Trending: All languages.